Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

awesome-ai-papers

This repository is used to collect papers and code in the field of AI.
https://github.com/songqiang321/awesome-ai-papers

Last synced: 10 days ago
JSON representation

  • CV

    • 3. CV Application

      • [paper - DeblurVSR](https://github.com/DachunKai/Ev-DeblurVSR)\]\[[Chain-of-Zoom](https://github.com/bryanswkim/Chain-of-Zoom)\]\[[4KAgent](https://github.com/taco-group/4KAgent)\]
      • [paper - ESRGAN](https://github.com/xinntao/Real-ESRGAN)\]\[[DreamClear](https://github.com/shallowdream204/DreamClear)\]
      • [paper - to-end-Autonomous-Driving](https://github.com/OpenDriveLab/End-to-end-Autonomous-Driving)\]\[[Awesome-LLM4AD](https://github.com/Thinklab-SJTU/Awesome-LLM4AD)\]
      • [paper - pytorch](https://github.com/yenchenlin/nerf-pytorch)\]\[[NeRF-Factory](https://github.com/kakaobrain/NeRF-Factory)\]\[[LERF](https://github.com/kerrj/lerf)\]\[[LangSplat](https://github.com/minghanqin/LangSplat)\]
      • [paper - lab/MagicDrive)\]\[[MagicDrive3D](https://github.com/flymin/MagicDrive3D)\]\[[MagicDriveDiT](https://github.com/flymin/MagicDriveDiT)\]\[[DiffusionDrive](https://github.com/hustvl/DiffusionDrive)\]\[[openemma](https://github.com/taco-group/openemma)\]\[[DrivingWorld](https://github.com/YvanYin/DrivingWorld)\]\[[AlphaDrive](https://github.com/hustvl/AlphaDrive)\]\[[Orion](https://github.com/xiaomi-mlab/Orion)\]\[[FSDrive](https://github.com/MIV-XJTU/FSDrive)\]
      • [paper - vilab/AnyDoor)\]\[[VideoAnydoor](https://videoanydoor.github.io)\]
      • [paper - research/InstantID)\]\[[InstantStyle](https://github.com/instantX-research/InstantStyle)\]\[[ID-Animator](https://github.com/ID-Animator/ID-Animator)\]\[[ConsistentID](https://github.com/JackAILab/ConsistentID)\]\[[PuLID](https://github.com/ToTheBeginning/PuLID)\]\[[ComfyUI-InstantID](https://github.com/ZHO-ZHO-ZHO/ComfyUI-InstantID)\]\[[StableAnimator](https://github.com/Francis-Rings/StableAnimator)\]\[[MV-Adapter](https://github.com/huanngzh/MV-Adapter)\]\[[InfiniteYou](https://github.com/bytedance/InfiniteYou)\]\[[USO](https://github.com/bytedance/USO)\]\[[UMO](https://github.com/bytedance/UMO)\]\[[Stand-In](https://github.com/WeChatCV/Stand-In)\]
      • [paper - Latex-OCR](https://github.com/RQLuo/MixTeX-Latex-OCR)\]\[[kosmos-2.5](https://github.com/microsoft/unilm/tree/master/kosmos-2.5)\]\[[gptpdf](https://github.com/CosmosShadow/gptpdf)\]\[[MegaParse](https://github.com/QuivrHQ/MegaParse)\]\[[omniparse](https://github.com/adithya-s-k/omniparse)\]\[[llama_parse](https://github.com/run-llama/llama_parse)\]\[[PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)\]\[[docling](https://github.com/DS4SD/docling)\]\[[ViTLP](https://github.com/Veason-silverbullet/ViTLP)\]\[[markitdown](https://github.com/microsoft/markitdown)\]\[[OCRmyPDF](https://github.com/ocrmypdf/OCRmyPDF)\]\[[DocTron-Formula](https://github.com/DocTron-hub/DocTron-Formula)\]
      • [paper - forge-layerdiffusion](https://github.com/layerdiffusion/sd-forge-layerdiffusion)\]\[[LayerDiffuse_DiffusersCLI](https://github.com/lllyasviel/LayerDiffuse_DiffusersCLI)\]\[[IC-Light](https://github.com/lllyasviel/IC-Light)\]\[[Paints-UNDO](https://github.com/lllyasviel/Paints-UNDO)\]
      • [paper - ml/prolificdreamer)\]\[[Metric3D](https://github.com/YvanYin/Metric3D)\]\[[ReconX](https://github.com/liuff19/ReconX)\]\[[VideoScene](https://github.com/hanyang-21/VideoScene)\]\[[DimensionX](https://github.com/wenqsun/DimensionX)\]\[[LLaMa-Mesh](https://github.com/nv-tlabs/LLaMa-Mesh)\]\[[DeepMesh](https://github.com/zhaorw02/DeepMesh)\]\[[MetaSpatial](https://github.com/PzySeere/MetaSpatial)\]\[[meshgpt-pytorch](https://github.com/lucidrains/meshgpt-pytorch)\]\[[ShapeLLM-Omni](https://github.com/JAMESYJL/ShapeLLM-Omni)\]
      • [deepfakes/faceswap - Live-Cam](https://github.com/hacksider/Deep-Live-Cam)\]\[[face-alignment](https://github.com/1adrianb/face-alignment)\]\[[roop](https://github.com/s0md3v/roop)\]\[[DeepFakeDefenders](https://github.com/VisionRush/DeepFakeDefenders)\]\[[HivisionIDPhotos](https://github.com/Zeyi-Lin/HivisionIDPhotos)\]\[[insightface](https://github.com/deepinsight/insightface)\]\[[VisoMaster](https://github.com/visomaster/VisoMaster)\]
      • [apollo - rpg/dagr)\]
      • [IOPaint - mmlab/PowerPaint)\]
      • [supervision - edge-platform/anomalib)\]
      • [MuseV
      • [paper - AI/stable-fast-3d)\]\[[ViewCrafter](https://github.com/Drexubery/ViewCrafter)\]\[[3DTopia-XL](https://github.com/3DTopia/3DTopia-XL)\]\[[TRELLIS](https://github.com/Microsoft/TRELLIS)\]\[[See3D](https://github.com/baaivision/See3D)\]\[[Awesome-LLM-3D](https://github.com/ActiveVisionLab/Awesome-LLM-3D)\]\[[MIDI-3D](https://github.com/VAST-AI-Research/MIDI-3D)\]\[[TripoSG](https://github.com/VAST-AI-Research/TripoSG)\]\[[cube](https://github.com/Roblox/cube)\]\[[Kiss3DGen](https://github.com/EnVision-Research/Kiss3DGen)\]\[[Direct3D-S2](https://github.com/DreamTechAI/Direct3D-S2)\]
      • [paper
      • [paper - AI/stable-point-aware-3d)\]\[[mvdust3r](https://github.com/facebookresearch/mvdust3r)\]\[[LHM](https://github.com/aigc3d/LHM)\]\[[LAM](https://github.com/aigc3d/LAM)\]\[[Difix3D](https://github.com/nv-tlabs/Difix3D)\]\[[Step1X-3D](https://github.com/stepfun-ai/Step1X-3D)\]\[[Matrix-3D](https://github.com/SkyworkAI/Matrix-3D)\]
      • [paper - HaoranWei/GOT-OCR2.0)\]\[[PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)\]\[[tesseract](https://github.com/tesseract-ocr/tesseract)\]\[[EasyOCR](https://github.com/JaidedAI/EasyOCR)\]\[[llm_aided_ocr](https://github.com/Dicklesworthstone/llm_aided_ocr)\]\[[surya](https://github.com/VikParuchuri/surya)\]\[[Umi-OCR](https://github.com/hiroi-sora/Umi-OCR)\]\[[zerox](https://github.com/getomni-ai/zerox)\]\[[RapidOCR](https://github.com/RapidAI/RapidOCR)\]\[[AdvancedLiterateMachinery](https://github.com/AlibabaResearch/AdvancedLiterateMachinery)\]
      • [paper - ai/DeepSeek-OCR)\]\[[Glyph](https://github.com/thu-coai/Glyph)\]\[[PIXEL](https://github.com/xplip/pixel)\]\[[deepseek-ocr.rs](https://github.com/TimmyOVO/deepseek-ocr.rs)\]\[[DeepOCR](https://github.com/pkulium/DeepOCR)\]
      • [paper - DM](https://github.com/dailenson/One-DM)\]
      • [paper
      • [paper
      • [link - anyone)\]\[[IDM-VTON](https://github.com/yisol/IDM-VTON)\]\[[IMAGDressing](https://github.com/muzishen/IMAGDressing)\]\[[CatVTON](https://github.com/Zheng-Chong/CatVTON)\]\[[Awesome-Try-On-Models](https://github.com/Zheng-Chong/Awesome-Try-On-Models)\]
      • [paper - OCR-App](https://github.com/AIAnytime/SmolDocling-OCR-App)\]\[[MonkeyOCR](https://github.com/Yuliang-Liu/MonkeyOCR)\]\[[dots.ocr](https://github.com/rednote-hilab/dots.ocr)\]\[[Logics-Parsing](https://github.com/alibaba/Logics-Parsing)\]
      • [paper
      • [link - anyone)\]\[[IDM-VTON](https://github.com/yisol/IDM-VTON)\]\[[IMAGDressing](https://github.com/muzishen/IMAGDressing)\]\[[CatVTON](https://github.com/Zheng-Chong/CatVTON)\]\[[Awesome-Try-On-Models](https://github.com/Zheng-Chong/Awesome-Try-On-Models)\]

    • 1. Basic for CV

      • [paper
      • [paper
      • [paper - residual-networks)\]\[[resnet_inference.py](https://github.com/zhangxiann/PyTorch_Practice/blob/master/lesson8/resnet_inference.py)\]
      • [paper
      • [paper - PyTorch](https://github.com/lukemelas/EfficientNet-PyTorch)\]\[[noisystudent](https://github.com/google-research/noisystudent)\]
      • [paper - V2](https://github.com/facebookresearch/ConvNeXt-V2)\]
      • [paper - deepmind/deepmind-research/tree/master/byol)\]\[[byol-pytorch](https://github.com/lucidrains/byol-pytorch)\]\[[simsiam](https://github.com/facebookresearch/simsiam)\]
      • [paper - Source-Code](https://github.com/computerhistory/AlexNet-Source-Code)\]

    • 4. Foundation Model

      • [paper - research/vision_transformer)\]\[[vit-pytorch](https://github.com/lucidrains/vit-pytorch)\]\[[efficientvit](https://github.com/mit-han-lab/efficientvit)\]\[[FasterViT](https://github.com/NVlabs/FasterViT)\]\[[EfficientFormer](https://github.com/snap-research/EfficientFormer)\]\[[Agent-Attention](https://github.com/LeapLabTHU/Agent-Attention)\]\[[T2T-ViT](https://github.com/yitu-opensource/T2T-ViT)\]\[[ViViT](https://arxiv.org/abs/2103.15691)\]
      • [paper
      • [paper - Transformer)\]\[[Video-Swin-Transformer](https://github.com/SwinTransformer/Video-Swin-Transformer)\]
      • [paper
      • [paper - pytorch](https://github.com/lucidrains/LVMAE-pytorch)\]\[[SparK](https://github.com/keyu-tian/SparK)\]
      • [paper - Adapter)\]
      • [paper - anything)\]
      • [paper - 6669f44df0d87d9c3bfb76de)\]\[[Inference code](https://huggingface.co/microsoft/Florence-2-large/blob/main/sample_inference.ipynb)\]\[[Florence-VL](https://github.com/JiuhaiChen/Florence-VL)\]
      • [paper
      • [paper
      • [paper - Anything)\]\[[Depth-Anything-V2](https://github.com/DepthAnything/Depth-Anything-V2)\]\[[PromptDA](https://github.com/DepthAnything/PromptDA)\]\[[Video-Depth-Anything](https://github.com/DepthAnything/Video-Depth-Anything)\]\[[ml-depth-pro](https://github.com/apple/ml-depth-pro)\]\[[DepthCrafter](https://github.com/Tencent/DepthCrafter)\]\[[rollingdepth](https://github.com/prs-eth/rollingdepth)\]\[[DepthAnythingAC](https://github.com/HVision-NKU/DepthAnythingAC)\]\[[DepthLM](https://github.com/facebookresearch/DepthLM_Official)\]
      • [paper
      • [paper
      • [paper
      • [pytorch-image-models
      • [paper
      • [paper
      • [paper
      • [paper - tokenizer)\]\[[titok-pytorch](https://github.com/lucidrains/titok-pytorch)\]\[[Randomized Autoregressive Visual Generation](https://arxiv.org/abs/2411.00776)\]\[[tokenize-anything](https://github.com/baaivision/tokenize-anything)\]\[[Cosmos-Tokenizer](https://github.com/NVIDIA/Cosmos-Tokenizer)\]\[[ViTok](https://arxiv.org/abs/2501.09755)\]\[[UniTok](https://github.com/FoundationVision/UniTok)\]\[[TokenFlow](https://github.com/ByteFlow-AI/TokenFlow)\]

    • 6. Image Editing

      • [paper - pix2pix)\]
      • [paper - E/DragonDiffusion)\]
      • [paper - Shi/DragDiffusion)\]
      • [paper - images/leditsplusplus/tree/main)\]\[[demo](https://huggingface.co/spaces/editing-images/leditsplusplus)\]
      • [paper
      • [paper - mgie)\]
      • [paper - uofa/Framer)\]\[[SG-I2V](https://github.com/Kmcode1/SG-I2V)\]\[[Go-with-the-Flow](https://github.com/Eyeline-Research/Go-with-the-Flow)\]
      • [paper - Diffusion-Model-Based-Image-Editing-Methods)\]
      • [paper
      • [paper - vilab/MimicBrush)\]\[[EchoMimic](https://github.com/antgroup/echomimic)\]\[[echomimic_v2](https://github.com/antgroup/echomimic_v2)\]\[[echomimic_v3](https://github.com/antgroup/echomimic_v3)\]\[[BrushNet](https://github.com/TencentARC/BrushNet)\]
      • [EditAnything - UltraEdit-ZHO](https://github.com/ZHO-ZHO-ZHO/ComfyUI-UltraEdit-ZHO)\]\[[libcom](https://github.com/bcmi/libcom)\]\[[Awesome-Image-Composition](https://github.com/bcmi/Awesome-Image-Composition)\]\[[RF-Solver-Edit](https://github.com/wangjiangshan0725/RF-Solver-Edit)\]\[[KV-Edit](https://github.com/Xilluill/KV-Edit)\]\[[HiDream-E1](https://github.com/HiDream-ai/HiDream-E1)\]\[[VAREdit](https://github.com/HiDream-ai/VAREdit)\]\[[Awesome-Image-Editing](https://github.com/FudanCVL/Awesome-Image-Editing)\]
      • [paper - ai/Step1X-Edit)\]\[[SuperEdit](https://github.com/bytedance/SuperEdit)\]\[[ICEdit](https://github.com/River-Zhang/ICEdit)\]\[[ImgEdit](https://github.com/PKU-YuanGroup/ImgEdit)\]
      • [paper - research/MagicQuill)\]
      • [paper - xw/DiffuEraser)\]\[[PhotoDoodle](https://github.com/showlab/PhotoDoodle)\]\[[VideoPainter](https://github.com/TencentARC/VideoPainter)\]
      • [paper
      • [paper - Image-Editing)\]
      • [paper
      • [paper

    • 2. Contrastive Learning

      • [paper - Predictive-Coding-PyTorch)\]
      • [paper
      • [paper
      • [paper - research/simclr)\]
      • [paper - pytorch](https://github.com/lucidrains/CoCa-pytorch)\]\[[multimodal](https://github.com/facebookresearch/multimodal)\]
      • [paper

    • 7. Object Detection

      • [paper - Research/detrex)\]\[[RT-DETR](https://github.com/lyuwenyu/RT-DETR)\]\[[rf-detr](https://github.com/roboflow/rf-detr)\]
      • [paper - noah/noah-research)\]
      • [paper - Research/GroundingDINO)\]\[[DINO-X](https://arxiv.org/abs/2411.14347)\]\[[OV-DINO](https://github.com/wanghao9610/OV-DINO)\]\[[OmDet](https://github.com/om-ai-lab/OmDet)\]\[[groundingLMM](https://github.com/mbzuai-oryx/groundingLMM)\]\[[DeepPerception](https://github.com/thunlp/DeepPerception)\]\[[Awesome-Visual-Grounding](https://github.com/linhuixiao/Awesome-Visual-Grounding)\]\[[DEIMv2](https://github.com/Intellindust-AI-Lab/DEIMv2)\]
      • [paper
      • [paper - BaseDetection/YOLOX)\]
      • [paper - cvc/yolo-world)\]
      • [paper - Research/T-Rex)\]\[[ChatRex](https://github.com/IDEA-Research/ChatRex)\]\[[RexSeek](https://github.com/IDEA-Research/RexSeek)\]\[[Rex-Thinker](https://github.com/IDEA-Research/Rex-Thinker)\]
      • [Detectron2 - mmlab/mmdetection)\]\[[MMDetection3D](https://github.com/open-mmlab/mmdetection3d)\]\[[detrex](https://github.com/IDEA-Research/detrex)\]\[[Ultralytics YOLO11](https://github.com/ultralytics/ultralytics)\]\[[AlphaPose](https://github.com/MVIG-SJTU/AlphaPose)\]\[[Anomalib](https://github.com/open-edge-platform/anomalib)\]
      • [paper - MIG/yolov10)\]\[[YOLOE](https://github.com/THU-MIG/yoloe)\]\[[YOLOv12](https://github.com/sunsmarterjie/yolov12)\]
      • [paper - 2-Net)\]
      • [paper - noah/Efficient-Computing/tree/master/Detection/Gold-YOLO)\]
      • [paper
      • [paper - FINE)\]

    • 8. Semantic Segmentation

      • [paper
      • [paper - anything)\]\[[SAM-Adapter-PyTorch](https://github.com/tianrun-chen/SAM-Adapter-PyTorch)\]\[[EditAnything](https://github.com/sail-sg/EditAnything)\]\[[SegmentAnything3D](https://github.com/Pointcept/SegmentAnything3D)\]\[[Semantic-Segment-Anything](https://github.com/fudan-zvg/Semantic-Segment-Anything)\]\[[Language Segment-Anything](https://github.com/luca-medeiros/lang-segment-anything)\]
      • [paper - UNet](https://github.com/milesial/Pytorch-UNet)\]\[[xLSTM-UNet-Pytorch](https://github.com/tianrun-chen/xLSTM-UNet-Pytorch)\]
      • [paper - IVA-Lab/FastSAM)\]\[[RobustSAM](https://github.com/robustsam/RobustSAM)\]\[[MobileSAM](https://github.com/ChaoningZhang/MobileSAM)\]
      • [paper - research/LISA)\]\[[VideoLISA](https://github.com/showlab/VideoLISA)\]\[[Seg-Zero](https://github.com/dvlab-research/Seg-Zero)\]
      • [paper - Anything)\]\[[Caption-Anything](https://github.com/ttengwang/Caption-Anything)\]\[[Tracking-Anything-with-DEVA](https://github.com/hkchengrex/Tracking-Anything-with-DEVA)\]\[[tracks-to-4d](https://github.com/NVlabs/tracks-to-4d)\]
      • [paper - Research/Grounded-Segment-Anything)\]\[[Grounded-SAM-2](https://github.com/IDEA-Research/Grounded-SAM-2)\]
      • [MMSegmentation - mmlab/mmdeploy)\]\[[Painter](https://github.com/baaivision/Painter)\]
      • [paper
      • [blog - research/Sa2VA)\]
      • [paper - Anything/PAM)\]
      • [paper - Seg)\]
      • [paper
      • [paper - 3d-objects)\]\[[SAM 3D Body](https://github.com/facebookresearch/sam-3d-body)\]
      • [paper - 3d-objects)\]\[[SAM 3D Body](https://github.com/facebookresearch/sam-3d-body)\]
      • [paper - ML/SocioReasoner)\]

    • 5. Generative Model (GAN and VAE)

      • [paper - GAN](https://github.com/eriklindernoren/PyTorch-GAN)\]\[[DCGAN](https://arxiv.org/abs/1511.06434)\]
      • [paper - transformers)\]\[[FQGAN](https://arxiv.org/abs/2411.16681)\]
      • [paper - pytorch](https://github.com/lucidrains/gigagan-pytorch)\]
      • [paper - Institute/StyleFeatureEditor)\]
      • [paper - VAE/blob/master/models/vq_vae.py)\]\[[vector-quantize-pytorch](https://github.com/lucidrains/vector-quantize-pytorch)\]
      • [paper - autoencoder)\]\[[Pytorch-VAE](https://github.com/AntixK/PyTorch-VAE)\]\[[VAE blog](https://lilianweng.github.io/posts/2018-08-12-vae/)\]\[[Glow](https://openai.com/index/glow)\]\[[RAE](https://github.com/bytetriper/RAE)\]
      • [paper - Transformer](https://github.com/chenllliang/DnD-Transformer)\]\[[chameleon](https://github.com/facebookresearch/chameleon)\]\[[Emu3](https://github.com/baaivision/Emu3)\]\[[BAGEL](https://github.com/ByteDance-Seed/Bagel)\]\[[NextStep-1](https://github.com/stepfun-ai/NextStep-1)\]
      • [pytorch-CycleGAN-and-pix2pix - turbo](https://github.com/GaParmar/img2img-turbo)\]
      • [paper
      • [paper - diffusion-pytorch](https://github.com/lucidrains/autoregressive-diffusion-pytorch)\]\[[NOVA](https://github.com/baaivision/NOVA)\]\[[DiSA](https://github.com/Qinyu-Allen-Zhao/DiSA)\]
      • [paper - MAGVIT2)\]\[[magvit2-pytorch](https://github.com/lucidrains/magvit2-pytorch)\]
      • [paper
      • [paper - Zero-star](https://github.com/WeichenFan/CFG-Zero-star)\]\[[Flow-GRPO](https://github.com/yifan123/flow_grpo)\]\[[DanceGRPO](https://arxiv.org/abs/2505.07818)\]\[[MixGRPO](https://github.com/Tencent-Hunyuan/MixGRPO)\]\[[Diffusion Meets Flow Matching](https://diffusionflow.github.io/)\]\[[MeanFlow](https://github.com/zhuyu-cs/MeanFlow)\]
      • [paper
      • [paper - vae-2-pytorch)\]
      • [paper - Gen](https://github.com/modelscope/Nexus-Gen)\]\[[BAGEL](https://github.com/ByteDance-Seed/Bagel)\]\[[MindOmni](https://github.com/TencentARC/MindOmni)\]
      • [paper - han-lab/hart)\]
      • [paper - Models-in-Vision-Survey)\]\[[Unified Multimodal Understanding and Generation Models](https://arxiv.org/abs/2505.02567)\]
      • [paper - Voken)\]\[[tokenize-anything](https://github.com/baaivision/tokenize-anything)\]\[[Cosmos-Tokenizer](https://github.com/NVIDIA/Cosmos-Tokenizer)\]\[[OmniTokenizer](https://github.com/FoundationVision/OmniTokenizer)\]\[[UniTok](https://github.com/FoundationVision/UniTok)\]\[[TokenFlow](https://github.com/ByteFlow-AI/TokenFlow)\]\[[Divot](https://github.com/TencentARC/Divot)\]\[[VidTok](https://github.com/microsoft/VidTok)\]\[[GigaTok](https://github.com/SilentView/GigaTok)\]\[[FlowMo](https://github.com/kylesargent/FlowMo)\]\[[Selftok](https://arxiv.org/abs/2505.07538)\]
      • [paper

    • 9. Video

      • [paper - NJU/VideoMAE)\]\[[VideoMAE V2](https://github.com/OpenGVLab/VideoMAEv2)\]
      • [paper - A-Protagonist)\]
      • [paper
      • [paper - oryx/Video-ChatGPT)\]\[[Video-LLaMA](https://github.com/DAMO-NLP-SG/Video-LLaMA)\]\[[MovieChat](https://github.com/rese1f/MovieChat)\]\[[Chat-UniVi](https://github.com/PKU-YuanGroup/Chat-UniVi)\]\[[GPT4Scene-and-VLN-R1](https://github.com/Qi-Zhangyang/GPT4Scene-and-VLN-R1)\]
      • [paper - Anything)\]\[[VideoChat-R1](https://github.com/OpenGVLab/VideoChat-R1)\]
      • [paper - Anything/tree/main/video_chat2)\]\[[PhyGenBench](https://github.com/OpenGVLab/PhyGenBench)\]\[[VideoReasonBench](https://arxiv.org/abs/2505.23359)\]
      • [paper
      • [Awesome-LLMs-for-Video-Understanding
      • [paper - pytorch](https://github.com/lucidrains/MIMO-pytorch)\]\[[StableV2V](https://github.com/AlonzoLeeeooo/StableV2V)\]\[[SpatialLM](https://manycore-research.github.io/SpatialLM/)\]\[[Spatial-MLLM](https://github.com/diankun-wu/Spatial-MLLM)\]
      • [paper - ai-lab/OmAgent)\]\[[vision-agent](https://github.com/landing-ai/vision-agent)\]
      • [paper
      • [paper - research/Sa2VA)\]\[[Vidi](https://github.com/bytedance/vidi)\]
      • [paper - Seed/VideoWorld)\]\[[LWM](https://github.com/LargeWorldModel/LWM)\]\[[iVideoGPT](https://github.com/thuml/iVideoGPT)\]
      • [paper - HPC-AI-Lab/Enhance-A-Video)\]\[[VideoSys](https://github.com/NUS-HPC-AI-Lab/VideoSys)\]\[[Magic-1-For-1](https://github.com/DA-Group-PKU/Magic-1-For-1)\]
      • [paper - JEPA 2 Blogpost](https://ai.meta.com/blog/v-jepa-2-world-model-benchmarks/)\]\[[V-JEPA](https://github.com/facebookresearch/jepa)\]\[[I-JEPA](https://github.com/facebookresearch/ijepa)\]\[[jepa-intuitive-physics](https://arxiv.org/abs/2502.11831)\]\[[LLM-JEPA](https://arxiv.org/abs/2509.14252)\]\[[DINO-WM](https://arxiv.org/abs/2411.04983)\]\[[Navigation World Models](https://github.com/facebookresearch/nwm)\]
      • [paper - research/CoDeF)\]
      • [paper - space/MiraData)\]
      • [paper - XL)\]\[[Video-XL-Pro](https://arxiv.org/abs/2503.18478)\]\[[LongVU](https://github.com/Vision-CAIR/LongVU)\]\[[VisionZip](https://github.com/dvlab-research/VisionZip)\]\[[TimeChat](https://github.com/RenShuhuai-Andy/TimeChat)\]\[[STORM](https://research.nvidia.com/labs/lpr/storm)\]\[[BIMBA](https://arxiv.org/abs/2503.09590)\]\[[Vamba](https://github.com/TIGER-AI-Lab/Vamba)\]\[[VideoMind](https://github.com/yeliudev/VideoMind)\]\[[chapter-llama](https://github.com/lucas-ventura/chapter-llama)\]\[[ViLAMP](https://github.com/steven-ccq/ViLAMP)\]\[[VideoDeepResearch](https://github.com/yhy-2000/VideoDeepResearch)\]\[[Video-RAG](https://github.com/Leon1207/Video-RAG-master)\]

    • 10. Survey for CV

      • [paper - Parameter-Efficient-Transfer-Learning)\]
      • [paper - vish/Beyond-INet)\]

  • Reinforcement Learning

    • 1.Basic for RL

      • [paper - PyTorch](https://github.com/nikhilbarhate99/PPO-PyTorch)\]\[[implementation-matters](https://github.com/MadryLab/implementation-matters)\]\[[PPOxFamily](https://github.com/opendilab/PPOxFamily)\]\[[The 37 Implementation Details of PPO](https://iclr-blog-track.github.io/2022/03/25/ppo-implementation-details/)\]\[[ppo-implementation-details](https://github.com/vwxyzjn/ppo-implementation-details)\]
      • [paper
      • [paper - Adventure](https://github.com/higgsfield/RL-Adventure)\]\[[deep-q-learning](https://github.com/keon/deep-q-learning)\]\[[Deep-RL-Keras](https://github.com/germain-hug/Deep-RL-Keras)\]
      • [paper - Adventure/blob/master/1.dqn.ipynb)\]
      • [blog - learning-an-introduction](https://github.com/ShangtongZhang/reinforcement-learning-an-introduction)\]\[[easy-rl](https://github.com/datawhalechina/easy-rl)\]\[[deep-rl-course](https://huggingface.co/learn/deep-rl-course/)\]\[[wangshusen/DRL](https://github.com/wangshusen/DRL)\]
      • [paper - ddpg](https://github.com/ghliu/pytorch-ddpg)\]
      • [paper - stanford/diffusion_policy)\]
      • [tianshou - berkeley/rlkit)\]\[[pytorch-a2c-ppo-acktr-gail](https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail)\]\[[Safe-Reinforcement-Learning-Baselines](https://github.com/chauncygu/Safe-Reinforcement-Learning-Baselines)\]\[[CleanRL](https://github.com/vwxyzjn/cleanrl)\]\[[openrl](https://github.com/OpenRL-Lab/openrl)\]\[[ElegantRL](https://github.com/AI4Finance-Foundation/ElegantRL)\]\[[spinningup](https://github.com/openai/spinningup)\]\[[gym](https://github.com/openai/gym)\]\[[Gymnasium](https://github.com/Farama-Foundation/Gymnasium)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper
      • [paper
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]
      • [paper - tensorflow](https://github.com/devsisters/DQN-tensorflow)\]\[[DQN_pytorch](https://github.com/dxyang/DQN_pytorch)\]

    • 2. LLM for decision making

  • NLP

    • 3. Pretraining

      • [paper
      • [paper
      • [paper - research/bert)\]\[[BERT-pytorch](https://github.com/codertimo/BERT-pytorch)\]\[[bert4torch](https://github.com/Tongjilibo/bert4torch)\]\[[bert4keras](https://github.com/bojone/bert4keras)\]\[[ModernBERT](https://github.com/AnswerDotAI/ModernBERT)\]\[[What Should We Learn From ModernBERT](https://jina.ai/news/what-should-we-learn-from-modernbert)\]
      • [paper - 3)\]\[[nanoGPT](https://github.com/karpathy/nanoGPT)\]\[[build-nanogpt](https://github.com/karpathy/build-nanogpt)\]\[[gpt-fast](https://github.com/pytorch-labs/gpt-fast)\]\[[modded-nanogpt](https://github.com/KellerJordan/modded-nanogpt)\]\[[nanotron](https://github.com/huggingface/nanotron)\]
      • [paper - RLHF](https://github.com/OpenLMLab/MOSS-RLHF)\]\[[nanochat](https://github.com/karpathy/nanochat)\]
      • [paper
      • [paper - of-thought-hub](https://github.com/FranxYao/chain-of-thought-hub)\]
      • [paper
      • [paper - cellar/beir)\]\[[AIR-Bench](https://github.com/AIR-Bench/AIR-Bench)\]
      • [paper
      • [paper - nlp/SimCSE)\]\[[AnglE ACL 2024](https://github.com/SeanLee97/AnglE)\]
      • [paper - text-and-code-embeddings)\]
      • [paper
      • [paper - xl)\]
      • [paper
      • [paper - BERT-wwm](https://github.com/ymcui/Chinese-BERT-wwm)\]
      • [paper - LM)\]\[[Megatron-2](https://arxiv.org/abs/2104.04473)\]\[[megatron sequence parallelism](https://arxiv.org/abs/2205.05198)\]\[[Scaling Language Model Training to a Trillion Parameters Using Megatron](https://developer.nvidia.com/blog/scaling-language-model-training-to-a-trillion-parameters-using-megatron)\]\[[picotron](https://github.com/huggingface/picotron)\]\[[nanotron](https://github.com/huggingface/nanotron)\]\[[DeepEP](https://github.com/deepseek-ai/DeepEP)\]
      • [paper
      • [paper
      • [paper - research/text-to-text-transfer-transformer)\]\[[t5-pytorch](https://github.com/conceptofmind/t5-pytorch)\]\[[t5-pegasus-pytorch](https://github.com/renmada/t5-pegasus-pytorch)\]\[[nanoT5](https://github.com/PiotrNawrot/nanoT5)\]\[[T5Gemma](https://arxiv.org/abs/2504.06225)\]
      • [paper - transformers)\]\[[model](https://huggingface.co/sentence-transformers)\]\[[vec2text](https://github.com/jxmorris12/vec2text)\]
      • [paper - research/generative_agents)\]\[[genagents](https://github.com/joonspk-research/genagents)\]\[[GPTeam](https://github.com/101dotxyz/GPTeam)\]
      • [paper - ai/guidance)\]
      • [paper - research/prompt-tuning)\]\[[soft-prompt-tuning](https://github.com/kipgparker/soft-prompt-tuning)\]\[[Prompt-Tuning](https://github.com/mkshing/Prompt-Tuning)\]
      • [paper
      • [paper - ai/studios/code-lora-from-scratch)\]\[[lora](https://github.com/cloneofsimo/lora)\]\[[dora](https://github.com/catid/dora)\]\[[MoRA](https://github.com/kongds/MoRA)\]\[[ziplora-pytorch](https://github.com/mkshing/ziplora-pytorch)\]\[[alpaca-lora](https://github.com/tloen/alpaca-lora)\]\[[lorax](https://github.com/predibase/lorax)\]\[[Text-to-LoRA](https://github.com/SakanaAI/text-to-lora)\]\[[Zero-Shot Prompt-to-Weights](https://arxiv.org/abs/2506.16406)\]
      • [paper - FP4)\]
      • [paper - pytorch](https://github.com/lucidrains/toolformer-pytorch)\]\[[conceptofmind/toolformer](https://github.com/conceptofmind/toolformer)\]\[[xrsrke/toolformer](https://github.com/xrsrke/toolformer)\]\[[Graph_Toolformer](https://github.com/jwzhanggy/Graph_Toolformer)\]
      • [paper
      • [paper - Agent](https://github.com/microsoft/RD-Agent)\]\[[TinyTroupe](https://github.com/microsoft/TinyTroupe)\]\[[NLWeb](https://github.com/microsoft/NLWeb)\]\[[Magentic-UI](https://github.com/microsoft/magentic-ui)\]
      • [paper - MT/StableToolBench)\]
      • [paper - pilot](https://github.com/Pythagora-io/gpt-pilot)\]\[[Scaling Large-Language-Model-based Multi-Agent Collaboration](https://arxiv.org/abs/2406.07155)\]\[[ProactiveAgent](https://github.com/thunlp/ProactiveAgent)\]\[[FilmAgent](https://github.com/HITsz-TMG/FilmAgent)\]
      • [paper - GSAI/YuLan-Rec)\]\[[Scaling Law of Large Sequential Recommendation Models](https://arxiv.org/abs/2311.11351)\]
      • [paper - nlp/tree-of-thought-llm)\]\[[Plug in and Play Implementation](https://github.com/kyegomez/tree-of-thoughts)\]\[[tree-of-thought-prompting](https://github.com/dave1010/tree-of-thought-prompting)\]
      • [paper - Edgerunners/Plan-and-Solve-Prompting)\]\[[maestro](https://github.com/Doriandarko/maestro)\]\[[TravelPlanner](https://github.com/OSU-NLP-Group/TravelPlanner)\]
      • [paper
      • [paper - refine)\]\[[MCT Self-Refine](https://github.com/trotsky1997/MathBlackBox)\]\[[SelFee](https://github.com/kaistAI/SelFee)\]
      • [blog - Second-Half/)\]\[[Language Agents](https://ysymyth.github.io/papers/Dissertation-finalized.pdf)\]\[[AI Agents for Beginners](https://github.com/microsoft/ai-agents-for-beginners)\]\[[LLMAgentPapers](https://github.com/zjunlp/LLMAgentPapers)\]\[[LLM-Agents-Papers](https://github.com/AGI-Edgerunners/LLM-Agents-Papers)\]\[[awesome-language-agents](https://github.com/ysymyth/awesome-language-agents)\]\[[Awesome-Papers-Autonomous-Agent](https://github.com/lafmdp/Awesome-Papers-Autonomous-Agent)\]\[[GUI-Agents-Paper-List](https://github.com/OSU-NLP-Group/GUI-Agents-Paper-List)\]\[[ai-agent-white-paper](https://arthurchiao.art/blog/ai-agent-white-paper-zh)\]\[[EMNLP 2024 Tutorial: Language Agents](https://language-agent-tutorial.github.io/)\]
      • [paper - llm)\]
      • [paper
      • [paper - pathways-next-generation-ai-architecture/)\]
      • [paper - futuredata/megablocks)\]
      • [paper
      • [paper
      • [paper - lab/stanford_alpaca)\]
      • [blog - Vicuna](https://github.com/Facico/Chinese-Vicuna)\]
      • [paper
      • [hf blog - rl-ppo blog](https://huggingface.co/blog/deep-rl-ppo)\]\[[OpenAI blog](https://openai.com/index/learning-from-human-preferences)\]\[[alignment blog](https://openai.com/blog/our-approach-to-alignment-research)\]\[[awesome-RLHF](https://github.com/opendilab/awesome-RLHF)\]
      • [paper
      • [paper - foundation/bitsandbytes)\]
      • [paper - foundation/bitsandbytes)\]
      • [paper - DASLab/gptq)\]\[[AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ)\]\[[QMoE](https://github.com/IST-DASLab/qmoe)\]\[[llmc](https://github.com/ModelTC/llmc)\]
      • [paper - foundation/bitsandbytes)\]\[[unsloth](https://github.com/unslothai/unsloth)\]\[[ir-qlora](https://github.com/htqin/ir-qlora)\]\[[fsdp_qlora](https://github.com/AnswerDotAI/fsdp_qlora)\]\[[QeRL](https://github.com/NVlabs/QeRL)\]
      • [paper
      • [paper - MARCO-Web-Search](https://github.com/microsoft/MS-MARCO-Web-Search)\]\[[WebAgent](https://github.com/Alibaba-NLP/DeepResearch)\]
      • [paper
      • [paper - from-feedback)\]
      • [paper - llama/codellama)\]\[[model](https://huggingface.co/codellama)\]\[[Code World Model](https://github.com/facebookresearch/cwm)\]\[[llamacoder](https://github.com/Nutlope/llamacoder)\]\[[CodeBERT](https://github.com/microsoft/CodeBERT)\]
      • [paper - MLSys-Lab/Efficient-LLMs-Survey)\]
      • [paper - eval](https://github.com/openai/human-eval)\]\[[CriticGPT](https://openai.com/index/finding-gpt4s-mistakes-with-gpt-4/)\]\[[On scalable oversight with weak LLMs judging strong LLMs](https://arxiv.org/abs/2407.04622)\]\[[OpenAI Codex CLI](https://github.com/openai/codex)\]\[[AGENTS.md](https://github.com/openai/agents.md)\]\[[Claude Code](https://github.com/anthropics/claude-code)\]\[[Gemini CLI](https://github.com/google-gemini/gemini-cli)\]\[[GitHub Copilot](https://github.blog/changelog/2025-05-19-github-copilot-coding-agent-in-public-preview/)\]\[[GitHub Copilot](https://github.com/microsoft/vscode-copilot-chat)\]\[[OpenCode](https://github.com/opencode-ai/opencode)\]\[[Claude Code Proxy](https://github.com/fuergaosi233/claude-code-proxy)\]\[[Anthropic API](https://api-docs.deepseek.com/zh-cn/guides/anthropic_api)\]
      • [paper - pytorch](https://github.com/lucidrains/PaLM-pytorch)\]\[[PaLM-rlhf-pytorch](https://github.com/lucidrains/PaLM-rlhf-pytorch)\]\[[PaLM](https://github.com/conceptofmind/PaLM)\]
      • [paper
      • [paper - llama/llama/tree/llama_v1)\]\[[llama.cpp](https://github.com/ggerganov/llama.cpp)\]\[[ollama](https://github.com/jmorganca/ollama)\]\[[llamafile](https://github.com/Mozilla-Ocho/llamafile)\]
      • [paper
      • [paper - deepmind/code_contests)\]\[[AlphaCode2_Tech_Report](https://storage.googleapis.com/deepmind-media/AlphaCode2/AlphaCode2_Tech_Report.pdf)\]
      • [paper - han-lab/llm-awq)\]\[[AutoAWQ](https://github.com/casper-hansen/AutoAWQ)\]\[[smoothquant](https://github.com/mit-han-lab/smoothquant)\]\[[OmniServe](https://github.com/mit-han-lab/omniserve)\]
      • [paper
      • [paper - project/starcoder)\]\[[bigcode-project](https://github.com/bigcode-project)\]\[[model](https://huggingface.co/bigcode)\]
      • [paper - LLM](https://github.com/bytedance/ABQ-LLM)\]\[[VPTQ](https://github.com/microsoft/VPTQ)\]\[[ppq](https://github.com/OpenPPL/ppq)\]\[[AIMET](https://github.com/quic/aimet)\]
      • [paper - transformer-lm)\]
      • [paper - 2)\]\[[llm.c](https://github.com/karpathy/llm.c)\]
      • [paper
      • [paper - llama/llama)\]\[[llama2.c](https://github.com/karpathy/llama2.c)\]\[[lit-llama](https://github.com/Lightning-AI/lit-llama)\]\[[litgpt](https://github.com/Lightning-AI/litgpt)\]
      • [paper - Transformers](https://github.com/Beomi/BitNet-Transformers)\]\[[BitNet b1.58](https://arxiv.org/abs/2402.17764)\]\[[BitNet a4.8](https://arxiv.org/abs/2411.04965)\]\[[BitNet b1.58 2B4T](https://arxiv.org/abs/2504.12285)\]\[[BitNet v2](https://arxiv.org/abs/2504.18415)\]\[[T-MAC](https://github.com/microsoft/T-MAC)\]\[[BitBLAS](https://github.com/microsoft/BitBLAS)\]\[[BiLLM](https://github.com/Aaronhuang-778/BiLLM)\]\[[decoupleQ](https://github.com/bytedance/decoupleQ)\]
      • [paper - AMP)\]
      • [paper - DASLab/qmoe)\]
      • [paper - Pruner)\]\[[Awesome-Efficient-LLM](https://github.com/horseee/Awesome-Efficient-LLM)\]
      • [paper
      • [paper
      • [paper - research/LongLoRA)\]
      • [paper - han-lab/streaming-llm)\]\[[SwiftInfer](https://github.com/hpcaitech/SwiftInfer)\]\[[SwiftInfer blog](https://hpc-ai.com/blog/colossal-ai-swiftinfer)\]\[[StreamingVLM](https://github.com/mit-han-lab/streaming-vlm)\]
      • [paper
      • [paper - org/llm-reasoners)\]\[[LLM Reasoners COLM 2024](https://arxiv.org/abs/2404.05221)\]\[[AgentGen KDD 2025](https://arxiv.org/abs/2408.00764)\]
      • [paper
      • [paper
      • [paper - RL](https://github.com/OpenManus/OpenManus-RL)\]
      • [paper - Song793/RestGPT)\]
      • [paper - ToolMaker)\]\[[trove](https://github.com/zorazrw/trove)\]\[[CREATOR](https://arxiv.org/abs/2305.14318)\]
      • [paper - models/llm_multiagent_debate)\]\[[Multi-Agents-Debate](https://github.com/Skytliang/Multi-Agents-Debate)\]
      • [paper - ai/OpenAgents)\]
      • [paper - AGI/AutoAgents)\]
      • [paper - cn/agents)\]\[[Symbolic Learning Enables Self-Evolving Agents](https://arxiv.org/abs/2406.18532)\]
      • [paper - arena-x/webarena)\]\[[visualwebarena](https://github.com/web-arena-x/visualwebarena)\]\[[agent-workflow-memory](https://github.com/zorazrw/agent-workflow-memory)\]\[[WindowsAgentArena](https://github.com/microsoft/WindowsAgentArena)\]
      • [paper - NLP-Group/Mind2Web)\]\[[Mind2Web 2](https://github.com/OSU-NLP-Group/Mind2Web-2)\]\[[AutoWebGLM](https://github.com/THUDM/AutoWebGLM)\]
      • [paper - science/PAE)\]
      • [paper - Planner)\]
      • [paper - ai/camel)\]\[[crab](https://github.com/camel-ai/crab)\]\[[OASIS](https://github.com/camel-ai/oasis)\]
      • [paper - ai/OSWorld)\]\[[AgentGym](https://github.com/WooooDyy/AgentGym)\]\[[Agent-as-a-Judge](https://arxiv.org/abs/2410.10934)\]\[[intellagent](https://github.com/plurai-ai/intellagent)\]\[[Survey on Evaluation of LLM-based Agents](https://arxiv.org/abs/2503.16416)\]\[[AgentRewardBench](https://github.com/McGill-NLP/agent-reward-bench)\]\[[TaskCraft](https://arxiv.org/abs/2506.10055)\]\[[OAgents](https://arxiv.org/abs/2506.15741)\]
      • [paper - Agent-Paper-List)\]\[[Advances and Challenges in Foundation Agents](https://arxiv.org/abs/2504.01990)\]\[[Awesome-Foundation-Agents](https://github.com/FoundationAgents/awesome-foundation-agents)\]
      • [paper - Agent-Survey)\]\[[LLM-Agent-Paper-Digest](https://github.com/XueyangFeng/LLM-Agent-Paper-Digest)\]\[[awesome-lifelong-llm-agent](https://github.com/qianlima-lab/awesome-lifelong-llm-agent)\]\[[Agentic Web](https://github.com/SafeRL-Lab/agentic-web)\]
      • [paper - zh](https://llmbook-zh.github.io/)\]\[[LLMsPracticalGuide](https://github.com/Mooler0410/LLMsPracticalGuide)\]\[[Foundations-of-LLMs](https://github.com/ZJU-LLMs/Foundations-of-LLMs)\]
      • [paper
      • [paper
      • [paper - nlp/ceval)\]\[[chinese-llm-benchmark](https://github.com/jeinlee1991/chinese-llm-benchmark)\]
      • [m3e-base - embedding-v2](https://huggingface.co/lier007/xiaobu-embedding-v2)\]\[[stella_en_1.5B_v5](https://huggingface.co/dunzhang/stella_en_1.5B_v5)\]\[[Conan-embedding-v2](https://huggingface.co/TencentBAC/Conan-embedding-v2)\]
      • [paper
      • [paper
      • [paper - MedLLM)\]
      • [paper - II](https://github.com/FreedomIntelligence/HuatuoGPT-II)\]\[[Medical_NLP](https://github.com/FreedomIntelligence/Medical_NLP)\]\[[Zhongjing](https://github.com/SupritYoung/Zhongjing)\]\[[MedicalGPT](https://github.com/shibing624/MedicalGPT)\]\[[huatuogpt-vision](https://github.com/freedomintelligence/huatuogpt-vision)\]\[[Chain-of-Diagnosis](https://github.com/FreedomIntelligence/Chain-of-Diagnosis)\]\[[BianCang](https://github.com/QLU-NLP/BianCang)\]\[[Llama3-OpenBioLLM-70B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-70B)\]\[[CareGPT](https://github.com/WangRongsheng/CareGPT)\]\[[HealthGPT](https://github.com/DCDmllm/HealthGPT)\]
      • [paper
      • [paper - wu/PMC-LLaMA)\]\[[MMedLM](https://github.com/MAGIC-AI4Med/MMedLM)\]
      • [paper - harvard/TxAgent)\]\[[MedAgent-Pro](https://arxiv.org/abs/2503.18968)\]
      • [paper - li/Instruction-Tuning-Survey)\]
      • [paper
      • [paper - in-Health/MedLLMsPracticalGuide)\]\[[LLM-for-Healthcare](https://github.com/KaiHe-better/LLM-for-Healthcare)\]\[[GMAI-MMBench](https://github.com/uni-medical/GMAI-MMBench)\]
      • [paper - LoRA/S-LoRA)\]\[[AdaLoRA](https://github.com/QingruZhang/AdaLoRA)\]\[[LoRAMoE](https://github.com/Ablustrund/LoRAMoE)\]\[[lorahub](https://github.com/sail-sg/lorahub)\]\[[O-LoRA](https://github.com/cmnfriend/O-LoRA)\]\[[qa-lora](https://github.com/yuhuixu1993/qa-lora)\]
      • [paper - Foundation/FinRL)\]
      • [paper - research/circuit_training)\]\[[semikong](https://github.com/aitomatic/semikong)\]\[[Automating GPU Kernel Generation](https://developer.nvidia.com/blog/automating-gpu-kernel-generation-with-deepseek-r1-and-inference-time-scaling)\]\[[CUDA-L1](https://github.com/deepreinforce-ai/CUDA-L1)\]
      • [paper
      • [paper
      • [paper - coai/BPO)\]
      • [paper - benchmark)\]\[[ARE](https://github.com/facebookresearch/meta-agents-research-environments)\]\[[DeepResearchGym](https://arxiv.org/abs/2505.19253)\]\[[DeepResearch Bench](https://arxiv.org/abs/2506.11763)\]\[[xbench](https://arxiv.org/abs/2506.13651)\]\[[MM-BrowseComp](https://arxiv.org/abs/2508.13186)\]
      • [paper - rlhf-pytorch](https://github.com/conceptofmind/LaMDA-rlhf-pytorch)\]
      • [paper - neox)\]
      • [paper - workshop)\]\[[model](https://huggingface.co/bigscience)\]
      • [paper - inc/Baichuan2)\]\[[BaichuanSEED](https://arxiv.org/abs/2408.15079)\]\[[Baichuan Alignment Technical Report](https://arxiv.org/abs/2410.14940)\]\[[KV Shifting Attention Enhances Language Modeling](https://arxiv.org/abs/2411.19574)\]\[[Baichuan-M1](https://arxiv.org/abs/2502.12671)\]\[[Baichuan-M2](https://arxiv.org/abs/2509.02208)\]
      • [paper
      • [paper
      • [paper
      • [paper - workshop/data-preparation)\]\[[dataset](https://huggingface.co/bigscience-data)\]
      • [paper
      • [paper - pytorch-fully-sharded-data-parallel-api/)\]\[[pytorch-fsdp](https://github.com/huggingface/blog/blob/main/zh/pytorch-fsdp.md)\]
      • [paper
      • [paper
      • [paper
      • [paper - takeshi188/zero_shot_cot)\]
      • [paper
      • [paper - research/t5x/blob/main/docs/models.md#flan-t5-checkpoints)\]
      • [paper - instruct)\]\[[open-instruct](https://github.com/allenai/open-instruct)\]\[[Multi-modal-Self-instruct](https://github.com/zwq2018/Multi-modal-Self-instruct)\]\[[evol-instruct](https://github.com/nlpxucan/evol-instruct)\]\[[MMEvol](https://arxiv.org/abs/2409.05840)\]\[[Automatic Instruction Evolving for Large Language Models](https://arxiv.org/abs/2406.00770)\]
      • [paper
      • [paper
      • [paper
      • [paper
      • [paper - science/mm-cot)\]
      • [paper - demonstrations)\]
      • [paper - machines/pal)\]\[[CodeAct](https://github.com/xingyaoww/code-act)\]
      • [paper - Impact-of-Reasoning-Step-Length-on-Large-Language-Models)\]
      • [paper - paper-li_mu.pdf)\]\[[ps-lite](https://github.com/dmlc/ps-lite)\]\[[Zero Bubble Pipeline Parallelism](https://arxiv.org/abs/2401.10241)\]\[[DualPipe](https://github.com/deepseek-ai/DualPipe)\]
      • [paper - AILab/flash-attention)\]
      • [paper
      • [paper
      • [paper - 3 to o3](https://cameronrwolfe.substack.com/p/llm-scaling-laws)\]
      • [paper - human-preferences)\]\[[lm-human-preference-details](https://github.com/vwxyzjn/lm-human-preference-details)\]
      • [paper - instructions)\]
      • [paper - Tuning-with-GPT-4/GPT-4-LLM)\]
      • [paper - rlhf)\]
      • [paper - coai/Safety-Prompts)\]\[[PurpleLlama](https://github.com/meta-llama/PurpleLlama)\]
      • [paper - ai/letta)\]\[[Zep](https://arxiv.org/abs/2501.13956)\]\[[zep-python](https://github.com/getzep/zep-python)\]\[[graphiti](https://github.com/getzep/graphiti)\]
      • [paper - LawLLM)\]
      • [paper - YuanGroup/ChatLaw)\]\[[HK-O1aw](https://github.com/HKAIR-Lab/HK-O1aw)\]
      • [paper - FinLLM)\]
      • [paper - DI/XuanYuan)\]
      • [paper - Foundation/FinGPT)\]
      • [paper - Foundation/FinGPT)\]
      • [paper
      • [paper - li/CMMLU)\]
      • [paper
      • [paper - rag)\]\[[CRAG](https://github.com/HuskyInSalt/CRAG)\]\[[Golden-Retriever](https://arxiv.org/abs/2408.00798)\]
      • [paper - KGLLM/RAG-Survey)\]\[[Modular RAG](https://arxiv.org/abs/2407.21059)\]
      • [paper
      • [paper - survey/Awesome-Robotics-Foundation-Models)\]\[[Awesome-Implicit-NeRF-Robotics](https://github.com/zubair-irshad/Awesome-Implicit-NeRF-Robotics)\]
      • [paper
      • [paper - of-thoughts)\]
      • [paper
      • [paper - calling)\]
      • [paper - CVC/GPT4Tools)\]
      • [paper - chen/ToolQA)\]\[[toolbench](https://github.com/sambanova/toolbench)\]\[[MetaTool Benchmark](https://arxiv.org/abs/2310.03128)\]
      • [paper - hwh/AutoCrawler)\]\[[gpt-crawler](https://github.com/BuilderIO/gpt-crawler)\]\[[webllama](https://github.com/McGill-NLP/webllama)\]\[[gpt-researcher](https://github.com/assafelovic/gpt-researcher)\]\[[skyvern](https://github.com/Skyvern-AI/skyvern)\]\[[Scrapegraph-ai](https://github.com/VinciGit00/Scrapegraph-ai)\]\[[Crawl4AI](https://github.com/unclecode/crawl4ai)\]\[[Firecrawl](https://github.com/mendableai/firecrawl)\]\[[crawlee-python](https://github.com/apify/crawlee-python)\]\[[Agent-E](https://github.com/EmergenceAI/Agent-E)\]\[[CyberScraper-2077](https://github.com/itsOwen/CyberScraper-2077)\]\[[browser-use](https://github.com/browser-use/browser-use)\]\[[BrowserOS](https://github.com/browseros-ai/BrowserOS)\]\[[nova-act](https://github.com/aws/nova-act)\]\[[ReaderLM-v2](https://huggingface.co/jinaai/ReaderLM-v2)\]
      • [paper - AI-Lab/Program-of-Thoughts)\]
      • [paper
      • [paper - teacher)\]
      • [paper
      • [paper - pytorch](https://github.com/lucidrains/RETRO-pytorch)\]
      • [paper - analysis)\]
      • [paper
      • [paper
      • [Transformer Circuits Thread - chapter1-transformer-interp.streamlit.app)\]\[[Awesome-Interpretability-in-Large-Language-Models](https://github.com/ruizheliUOA/Awesome-Interpretability-in-Large-Language-Models)\]\[[TransformerLens](https://github.com/TransformerLensOrg/TransformerLens)\]\[[inseq](https://github.com/inseq-team/inseq)\]
      • [paper - NLP/LIMO)\]\[[LIMR](https://github.com/GAIR-NLP/LIMR)\]\[[LIMOPro](https://github.com/GAIR-NLP/LIMOPro)\]\[[LIMI](https://github.com/GAIR-NLP/LIMI)\]
      • [paper - research/Eureka)\]\[[DrEureka](https://github.com/eureka-research/DrEureka)\]\[[MM-EUREKA](https://github.com/ModalMinds/MM-EUREKA)\]
      • [paper - Alignment/safe-rlhf)\]\[[align-anything](https://github.com/PKU-Alignment/align-anything)\]\[[Safe-Policy-Optimization](https://github.com/PKU-Alignment/Safe-Policy-Optimization)\]
      • [paper
      • [paper - Embodied-AI/RoboGen)\]\[[Genesis](https://github.com/Genesis-Embodied-AI/Genesis)\]\[[RoboTwin](https://github.com/robotwin-Platform/RoboTwin)\]
      • [paper - 2)\]\[[RT-H: Action Hierarchies Using Language](https://arxiv.org/abs/2403.01823)\]\[[RoboMamba](https://arxiv.org/abs/2406.04339)\]
      • [paper - E)\]
      • [paper - research/robotics_transformer)\]\[[IRASim](https://github.com/bytedance/IRASim)\]
      • [link
      • [paper
      • [paper
      • [paper - group/textgrad)\]\[[appl](https://github.com/appl-team/appl)\]\[[okhat/blog](https://github.com/okhat/blog/blob/main/2024.09.impact.md)\]\[[PromptWizard](https://github.com/microsoft/PromptWizard)\]\[[SPO](https://arxiv.org/abs/2502.06855)\]\[[TPO](https://github.com/yafuly/TPO)\]\[[Text2Grad](https://github.com/microsoft/Text2Grad)\]\[[Llama Prompt Ops](https://github.com/meta-llama/llama-prompt-ops)\]\[[Promptomatix](https://github.com/SalesforceAIResearch/promptomatix)\]\[[Promptify](https://github.com/promptslab/Promptify)\]
      • [paper - token-nq)\]\[[docs](https://huggingface.co/docs/transformers/main/model_doc/rag)\]\[[FAISS](https://github.com/facebookresearch/faiss)\]\[[REFRAG](https://arxiv.org/abs/2509.01092)\]
      • [paper - embeddings-v2](https://huggingface.co/jinaai/jina-embeddings-v2-base-en)\]\[[jina-reranker-v2](https://huggingface.co/jinaai/jina-reranker-v2-base-multilingual)\]\[[reader-lm-1.5b](https://huggingface.co/jinaai/reader-lm-1.5b)\]\[[ReaderLM-v2](https://huggingface.co/jinaai/ReaderLM-v2)\]\[[pe_rank](https://github.com/liuqi6777/pe_rank)\]\[[Jina CLIP](https://arxiv.org/abs/2405.20204)\]\[[jina-embeddings-v3](https://arxiv.org/abs/2409.10173)\]\[[jina-embeddings-v4](https://arxiv.org/abs/2506.18902)\]\[[jina-reranker-v3](https://arxiv.org/abs/2509.25085)\]
      • [paper
      • [paper
      • [paper - cn/RecurrentGPT)\]
      • [paper - sys/FastChat/tree/main/fastchat/llm_judge)\]
      • [paper - crfm/helm)\]
      • [paper
      • [paper
      • [paper
      • [paper - Quantization-Papers](https://github.com/Zhen-Dong/Awesome-Quantization-Papers)\]\[[Awesome-Model-Quantization](https://github.com/Efficient-ML/Awesome-Model-Quantization)\]\[[qllm-eval](https://github.com/thu-nics/qllm-eval)\]\[[Awesome-Token-level-Model-Compression](https://github.com/xuyang-liu16/Awesome-Token-level-Model-Compression)\]
      • [paper - hallucination-survey)\]
      • [paper
      • [paper - 2.0)\]
      • [paper - refinedweb)\]
      • [paper
      • [paper - ai/aiconfig/tree/main/cookbooks/Chain-of-Verification)\]
      • [paper
      • [paper - NLP/factool)\]\[[OlympicArena](https://github.com/GAIR-NLP/OlympicArena)\]\[[FActScore](https://arxiv.org/abs/2305.14251)\]
      • [paper - Foundation/FinGPT/tree/master/fingpt/FinGPT_RAG/instruct-FinGPT)\]
      • [paper - Edgerunners/LLM-Adapters)\]
      • [paper - REACT)\]\[[AutoAct](https://github.com/zjunlp/AutoAct)\]
      • [paper - instruction-learning)\]
      • [paper
      • [paper
      • [paper - science/auto-cot)\]
      • [paper
      • [paper - ai/cumulative-reasoning)\]\[[On the Diagram of Thought](https://arxiv.org/abs/2409.10038)\]
      • [paper - deepmind/opro)\]
      • [paper - misalignment)\]\[[agentic-misalignment](https://github.com/anthropic-experimental/agentic-misalignment)\]\[[Alignment faking](https://www.anthropic.com/research/alignment-faking)\]
      • [paper - self-play)\]\[[Self-Adapting Language Models](https://github.com/Continual-Intelligence/SEAL)\]\[[SPIRAL](https://github.com/spiral-rl/spiral)\]
      • [paper - Corpus-Indexer-NCI)\]\[[DSI-transformers](https://github.com/ArvinZhuang/DSI-transformers)\]\[[GDR EACL 2024 Oral](https://arxiv.org/abs/2401.10487)\]
      • [paper - EM-pytorch)\]
      • [paper - RLAIF](https://github.com/mengdi-li/awesome-RLAIF)\]
      • [paper - Alignment](https://github.com/PKU-Alignment)\]\[[webpage](https://alignmentsurvey.com/)\]
      • [paper
      • [paper
      • [paper - LLM-hallucination)\]\[[Awesome-MLLM-Hallucination](https://github.com/showlab/Awesome-MLLM-Hallucination)\]
      • [paper - Lab/ATLAS)\]
      • [paper - mitchell/direct-preference-optimization)\]\[[trl](https://github.com/huggingface/trl)\]\[[dpo_trainer](https://github.com/huggingface/trl/blob/main/trl/trainer/dpo_trainer.py)\]
      • [paper
      • [paper
      • [paper - aim)\]\[[An Empirical Study of Autoregressive Pre-training from Videos](https://arxiv.org/abs/2501.05453)\]
      • [paper - IPADS/PowerInfer)\]\[[llama.cpp](https://github.com/ggerganov/llama.cpp)\]\[[airllm](https://github.com/lyogavin/airllm)\]\[[PowerInfer-2](https://arxiv.org/abs/2406.06282)\]\[[PowerServe](https://github.com/powerserve-project/PowerServe)\]\[[prima.cpp](https://github.com/Lizonghang/prima.cpp)\]
      • [paper - Adapter)\]
      • [paper
      • [paper - of-experts](https://github.com/lucidrains/mixture-of-experts)\]
      • [paper - media/gemini/gemini_1_report.pdf)\]\[[Gemini 1.5](https://arxiv.org/abs/2403.05530)\]\[[Gemini 2.5](https://arxiv.org/abs/2507.06261)\]\[[Unofficial Implementation](https://github.com/kyegomez/Gemini)\]\[[MiniGemini](https://github.com/dvlab-research/MGM)\]\[[Gemini Fullstack LangGraph Quickstart](https://github.com/google-gemini/gemini-fullstack-langgraph-quickstart)\]\[[GenAI Processors](https://github.com/google-gemini/genai-processors)\]
      • [paper - MLLM/Woodpecker)\]
      • [paper - Implementation](https://github.com/davidmrau/mixture-of-experts)\]
      • [paper
      • [paper
      • [paper - inference)\]\[[model](https://huggingface.co/mistralai)\]\[[mistral-finetune](https://github.com/mistralai/mistral-finetune)\]
      • [paper - 4o](https://openai.com/index/hello-gpt-4o/)\]\[[GPT-4o System Card](https://arxiv.org/abs/2410.21276)\]
      • [paper - compass/MathBench)\]\[[OlympiadBench](https://github.com/OpenBMB/OlympiadBench)\]\[[Math-Verify](https://github.com/huggingface/Math-Verify)\]\[[MathPile](https://github.com/GAIR-NLP/MathPile)\]\[[DeepMath-103K](https://arxiv.org/abs/2504.11456)\]\[[VCBench](https://arxiv.org/abs/2504.18589)\]
      • [paper - 1T](https://github.com/mlfoundations/MINT-1T)\]\[[multimodal_textbook](https://github.com/DAMO-NLP-SG/multimodal_textbook)\]
      • [paper - math/MetaMath)\]\[[MathCoder](https://github.com/mathllm/MathCoder)\]
      • [paper - parameter-efficient-tuning)\]
      • [paper - research/adapter-bert)\]\[[unify-parameter-efficient-tuning](https://github.com/jxhe/unify-parameter-efficient-tuning)\]
      • [paper - tuning-v2)\]\[[pet](https://github.com/timoschick/pet)\]\[[PrefixTuning](https://github.com/XiangLi1999/PrefixTuning)\]
      • [paper - tuning)\]
      • [paper
      • [paper
      • [paper - Collection)\]
      • [paper
      • [paper - Factory](https://github.com/Zefan-Cai/KVCache-Factory)\]\[[SpecInfer](https://arxiv.org/abs/2305.09781)\]
      • [paper
      • [paper - LLM](https://github.com/deepseek-ai/DeepSeek-LLM)\]\[[DeepSeek-V2](https://github.com/deepseek-ai/DeepSeek-V2)\]\[[DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3)\]\[[DeepSeek-Coder](https://github.com/deepseek-ai/DeepSeek-Coder)\]\[[open-infra-index](https://github.com/deepseek-ai/open-infra-index)\]
      • [paper - inference)\]\[[megablocks-public](https://github.com/mistralai/megablocks-public)\]\[[model](https://huggingface.co/mistralai)\]\[[blog](https://mistral.ai/news/mixtral-of-experts/)\]\[[Chinese-Mixtral-8x7B](https://github.com/HIT-SCIR/Chinese-Mixtral-8x7B)\]\[[Chinese-Mixtral](https://github.com/ymcui/Chinese-Mixtral)\]
      • [paper - ai/DeepSeek-MoE)\]
      • [paper
      • [paper - rewarding-lm-pytorch)\]\[[Meta-Rewarding Language Models](https://arxiv.org/abs/2407.19594)\]\[[Self-Taught Evaluators](https://arxiv.org/abs/2408.02666)\]
      • [paper - ai/DeepSeek-Coder)\]
      • [paper - survey](https://github.com/ulab-uiuc/AGI-survey)\]
      • [paper - 460M-1T)\]\[[MobiLlama](https://github.com/mbzuai-oryx/MobiLlama)\]\[[Steel-LLM](https://github.com/zhanshijinwat/Steel-LLM)\]\[[minimind](https://github.com/jingyaogong/minimind)\]\[[Cortex](https://github.com/qibin0506/Cortex)\]\[[tiny-llm-zh](https://github.com/wdndev/tiny-llm-zh)\]\[[SkyLadder](https://github.com/sail-sg/SkyLadder)\]
      • [paper
      • [paper - discover)\]\[[SELF-DISCOVER](https://github.com/kailashsp/SELF-DISCOVER)\]
      • [paper
      • [paper - Knowledge-Distillation-of-LLMs)\]
      • [paper - project/vllm)\]\[[FastChat](https://github.com/lm-sys/FastChat)\]\[[ollama](https://github.com/jmorganca/ollama)\]\[[Nano vLLM](https://github.com/GeeeekExplorer/nano-vllm)\]\[[Inside vLLM](https://www.aleksagordic.com/blog/vllm)\]
      • [paper
      • [paper - 2-a-large-scale-foundation-world-model)\]\[[Genie 3](https://deepmind.google/discover/blog/genie-3-a-new-frontier-for-world-models/)\]\[[genie2-pytorch](https://github.com/lucidrains/genie2-pytorch)\]\[[TinyWorlds](https://github.com/AlmondGod/tinyworlds)\]\[[GameNGen](https://arxiv.org/abs/2408.14837)\]\[[GameGen-X](https://github.com/GameGen-X/GameGen-X)\]\[[GameFactory](https://github.com/KwaiVGI/GameFactory)\]\[[Unbounded](https://arxiv.org/abs/2410.18975)\]\[[open-oasis](https://github.com/etched-ai/open-oasis)\]\[[DIAMOND](https://diamond-wm.github.io)\]\[[WHAM](https://huggingface.co/microsoft/wham)\]\[[dreamerv3](https://www.nature.com/articles/s41586-025-08744-2)\]\[[AssistanceZero](https://github.com/cassidylaidlaw/minecraft-building-assistance-game)\]\[[MineWorld](https://github.com/microsoft/MineWorld)\]\[[Multiverse](https://github.com/EnigmaLabsAI/multiverse)\]\[[Matrix-Game](https://github.com/SkyworkAI/Matrix-Game)\]\[[Hunyuan-GameCraft-1.0](https://github.com/Tencent-Hunyuan/Hunyuan-GameCraft-1.0)\]\[[Game-TARS](https://arxiv.org/abs/2510.23691)\]
      • [paper
      • [paper
      • [paper - handbook)\]
      • [blog
      • [paper - attention-pytorch](https://github.com/lucidrains/ring-attention-pytorch)\]\[[ring-flash-attention](https://github.com/zhuzilin/ring-flash-attention)\]\[[local-attention](https://github.com/lucidrains/local-attention)\]\[[tree_attention](https://github.com/Zyphra/tree_attention)\]
      • [paper
      • [paper - to-strong)\]\[[Prover-Verifier](https://arxiv.org/abs/2407.13692)\]\[[weak-to-strong-deception](https://github.com/keven980716/weak-to-strong-deception)\]\[[Evolving Alignment via Asymmetric Self-Play](https://arxiv.org/abs/2411.00062)\]\[[easy-to-hard](https://github.com/Edward-Sun/easy-to-hard)\]\[[Debate Helps Weak-to-Strong Generalization](https://arxiv.org/abs/2501.13124)\]\[[Detecting misbehavior in frontier reasoning models](https://openai.com/index/chain-of-thought-monitoring)\]
      • [paper
      • [paper - models)\]\[[The Geometry of Concepts: Sparse Autoencoder Feature Structure](https://arxiv.org/abs/2410.19750)\]
      • [paper
      • [paper
      • [paper - Code-LLM](https://github.com/codefuse-ai/Awesome-Code-LLM)\]\[[MFTCoder](https://github.com/codefuse-ai/MFTCoder)\]\[[Awesome-Code-LLM](https://github.com/huybery/Awesome-Code-LLM)\]\[[CodeFuse-muAgent](https://github.com/codefuse-ai/CodeFuse-muAgent)\]\[[Awesome-Code-Intelligence](https://github.com/QiushiSun/Awesome-Code-Intelligence)\]
      • [paper - lab/HallusionBench)\]\[[LRM-FactEval](https://arxiv.org/abs/2505.23646)\]
      • [paper - LLMs-on-device](https://github.com/NexaAI/Awesome-LLMs-on-device)\]
      • [paper
      • [paper
      • [paper
      • [paper - Context-Data-Engineering)\]
      • [paper - LLMs-Datasets](https://github.com/lmmlzn/Awesome-LLMs-Datasets)\]
      • [paper - ai/Yi)\]\[[Yi-1.5](https://github.com/01-ai/Yi-1.5)\]
      • [paper - cdn.anthropic.com/fed9cc193a14b84131812372d8d5857f8f304c52/Model_Card_Claude_3_Addendum.pdf)\]\[[Introducing Claude 4](https://www.anthropic.com/news/claude-4)\]
      • [paper - project/starcoder2)\]\[[starcoder.cpp](https://github.com/bigcode-project/starcoder.cpp)\]
      • [paper - 9b-20241220-technical-report)\]\[[AgentCPM-GUI](https://github.com/OpenBMB/AgentCPM-GUI)\]
      • [paper - NLP-Group/SeeAct)\]\[[WebDreamer](https://github.com/OSU-NLP-Group/WebDreamer)\]
      • [paper
      • [paper - GaLore](https://github.com/VITA-Group/Q-GaLore)\]\[[WeLore](https://github.com/VITA-Group/WeLore)\]\[[Fira](https://github.com/xichen-fy/Fira)\]
      • [paper
      • [paper
      • [paper - ulysses)\]\[[unofficial code](https://github.com/feifeibear/long-context-attention/blob/main/yunchang/ulysses/attn_layer.py)\]\[[MagiAttention](https://github.com/SandAI-org/MagiAttention)\]
      • [paper - interpreter](https://github.com/e2b-dev/code-interpreter)\]\[[open-interpreter](https://github.com/KillianLucas/open-interpreter)\]
      • [paper - uiuc/magicoder)\]
      • [blog - org/grok-1)\]\[[model](https://huggingface.co/xai-org/grok-1)\]\[[grok-prompts](https://github.com/xai-org/grok-prompts)\]\[[modelscope](https://modelscope.cn/models/AI-ModelScope/grok-1/summary)\]\[[hpcai-tech/grok-1](https://huggingface.co/hpcai-tech/grok-1)\]\[[dbrx](https://github.com/databricks/dbrx)\]\[[Command R+](https://huggingface.co/CohereForAI/c4ai-command-r-plus)\]\[[Command A](https://arxiv.org/abs/2504.00698)\]\[[snowflake-arctic](https://github.com/Snowflake-Labs/snowflake-arctic)\]
      • [paper - Factory)\]\[[360-LLaMA-Factory](https://github.com/Qihoo360/360-LLaMA-Factory)\]\[[EasyR1](https://github.com/hiyouga/EasyR1)\]
      • [paper
      • [paper - model-merge)\]
      • [paper - ai/OSWorld)\]\[[aguvis](https://github.com/xlang-ai/aguvis)\]\[[Large Action Models](https://arxiv.org/abs/2412.10047)\]
      • [paper - proj/AlphaFin)\]
      • [paper - Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)\]
      • [paper - a-p/COIG-CQIA)\]
      • [paper - Stars)\]\[[LLMTest_NeedleInAHaystack](https://github.com/gkamradt/LLMTest_NeedleInAHaystack)\]\[[RULER](https://github.com/NVIDIA/RULER)\]\[[LooGLE](https://github.com/bigai-nlco/LooGLE)\]\[[LongBench](https://github.com/THUDM/LongBench)\]\[[google-deepmind/loft](https://github.com/google-deepmind/loft)\]
      • [paper - Ye/ToolEyes)\]
      • [paper
      • [paper
      • [paper
      • [paper
      • [paper - rag-learning](https://github.com/mangopy/direct-rag-learning)\]\[[GenRank](https://arxiv.org/abs/2505.04180)\]
      • [paper - sciencelab/GraphGen)\]\[[SynthQuestions](https://arxiv.org/abs/2506.03968)\]
      • [paper - V](https://github.com/OpenBMB/MiniCPM-V)\]
      • [paper - Bench](https://github.com/hemingkx/Spec-Bench)\]
      • [paper - Agent-Survey](https://github.com/OS-Agent-Survey/OS-Agent-Survey)\]\[[ACU](https://github.com/francedot/acu)\]\[[Large Language Model-Brained GUI Agents: A Survey](https://arxiv.org/abs/2411.18279)\]\[[LLM-Powered GUI Agents in Phone Automation](https://arxiv.org/abs/2504.19838)\]\[[Aguvis](https://arxiv.org/abs/2412.04454)\]\[[awesome-computer-use](https://github.com/ranpox/awesome-computer-use)\]
      • [paper - dynamics)\]
      • [paper
      • [paper - transformer-pytorch](https://github.com/lucidrains/infini-transformer-pytorch)\]\[[InfiniTransformer](https://github.com/Beomi/InfiniTransformer)\]\[[infini-mini-transformer](https://github.com/jiahe7ay/infini-mini-transformer)\]\[[megalodon](https://github.com/XuezheMax/megalodon)\]\[[InfiniteHiP](https://arxiv.org/abs/2502.08910)\]
      • [paper - community/TrustRAG)\]
      • [paper
      • [paper - grpo](https://github.com/open-thought/tiny-grpo)\]\[[simple_GRPO](https://github.com/lsdefine/simple_GRPO)\]\[[GRPO-Zero](https://github.com/policy-gradient/GRPO-Zero)\]\[[grpo-flat](https://github.com/XU-YIJIE/grpo-flat)\]\[[kl-rel-to-ref-in-rl-zh](https://tongyx361.github.io/blogs/posts/kl-rel-to-ref-in-rl-zh)\]\[[Unsloth GRPO](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_(4B)-GRPO.ipynb)\]
      • [paper - NLPIR/GenIR-Survey)\]\[[Alipay Search](https://arxiv.org/abs/2503.21098)\]
      • [paper - Classification)\]
      • [paper
      • [paper - LLM-Inference](https://github.com/xlite-dev/Awesome-LLM-Inference)\]\[[A Survey on Inference Engines for Large Language Models](https://arxiv.org/abs/2505.01658)\]\[[Awesome-Generation-Acceleration](https://github.com/xuyang-liu16/Awesome-Generation-Acceleration)\]\[[Speed Always Wins](https://arxiv.org/abs/2508.09834)\]
      • [paper - ai-lab/Consistency_LLM)\]\[[LookaheadDecoding](https://github.com/hao-ai-lab/LookaheadDecoding)\]\[[Lookahead](https://github.com/alipay/PainlessInferenceAcceleration)\]
      • [paper
      • [paper - Agents/Cradle)\]
      • [paper - ai/DeepSeek-V2)\]\[[DeepSeek-V2.5](https://huggingface.co/deepseek-ai/DeepSeek-V2.5)\]
      • [blog
      • [paper
      • [paper - rep)\]
      • [paper - play Methods in Reinforcement Learning](https://arxiv.org/abs/2408.01072)\]
      • [paper - Factory](https://github.com/Zefan-Cai/KVCache-Factory)\]\[[InfiniGen](https://github.com/snu-comparch/InfiniGen)\]\[[kvpress](https://github.com/NVIDIA/kvpress)\]\[[KIVI](https://github.com/jy-yuan/KIVI)\]\[[KVQuant](https://github.com/SqueezeAILab/KVQuant)\]\[[Awesome-KV-Cache-Compression](https://github.com/October2001/Awesome-KV-Cache-Compression)\]\[[R-KV](https://github.com/Zefan-Cai/R-KV)\]\[[kvcached](https://github.com/ovg-project/kvcached)\]
      • [paper
      • [paper
      • [paper
      • [awesome-llm-apps - Domain-LLM](https://github.com/luban-agi/Awesome-Domain-LLM)\]\[[agents](https://github.com/livekit/agents)\]\[[ai-app-lab](https://github.com/volcengine/ai-app-lab)\]
      • [paper - nlp/SWE-agent)\]\[[mini SWE-agent](https://github.com/SWE-agent/mini-swe-agent)\]\[[swe-bench-technical-report](https://www.cognition-labs.com/post/swe-bench-technical-report)\]\[[SWE-smith](https://github.com/SWE-bench/SWE-smith)\]\[[CodeR](https://github.com/NL2Code/CodeR)\]\[[Lingma-SWE-GPT](https://github.com/LingmaTongyi/Lingma-SWE-GPT)\]\[[SWE-Gym](https://github.com/SWE-Gym/SWE-Gym)\]\[[MarsCode Agent](https://arxiv.org/abs/2409.00899)\]\[[SWE-Fixer](https://github.com/InternLM/SWE-Fixer)\]\[[SWE-RL](https://arxiv.org/abs/2502.18449)\]\[[SWE-Lancer](https://github.com/openai/SWELancer-Benchmark)\]\[[multi-swe-bench](https://github.com/multi-swe-bench/multi-swe-bench)\]\[[SWE-bench-Live](https://github.com/microsoft/SWE-bench-Live)\]\[[CodeFuse-CGM](https://github.com/codefuse-ai/CodeFuse-CGM)\]\[[DeepSWE](https://github.com/agentica-project/rllm/tree/main/examples/swe)\]\[[Skywork-SWE](https://arxiv.org/abs/2506.19290)\]\[[SWE-Swiss](https://github.com/zhenyuhe00/SWE-Swiss)\]\[[SWE-Bench Pro](https://github.com/scaleapi/SWE-bench_Pro-os)\]
      • [paper - rpm-bench)\]
      • [paper - ai/DeepSeek-Math)\]\[[Math-Shepherd](https://arxiv.org/abs/2312.08935)\]\[[DeepSeek-Prover-V1.5](https://github.com/deepseek-ai/DeepSeek-Prover-V1.5)\]\[[DeepSeek-Prover-V2](https://github.com/deepseek-ai/DeepSeek-Prover-V2)\]\[[Kimina-Prover Preview](https://arxiv.org/abs/2504.11354)\]\[[Goedel-Prover-V2](https://github.com/Goedel-LM/Goedel-Prover-V2)\]\[[BFS-Prover](https://arxiv.org/abs/2502.03438)\]\[[MPS-Prover](https://arxiv.org/abs/2505.10962)\]\[[DeepTheorem](https://arxiv.org/abs/2505.23754)\]\[[CriticLean](https://github.com/multimodal-art-projection/CriticLean)\]\[[StepFun-Prover-Preview](https://github.com/stepfun-ai/StepFun-Prover-Preview)\]\[[Seed-Prover](https://github.com/ByteDance-Seed/Seed-Prover)\]
      • [paper - Math)\]
      • [paper
      • [paper - RL/PRIME)\]
      • [paper
      • [paper - models/octo)\]\[[BodyTransformer](https://github.com/carlosferrazza/BodyTransformer)\]\[[crossformer](https://github.com/rail-berkeley/crossformer)\]\[[VideoMimic](https://arxiv.org/abs/2505.03729)\]
      • [paper
      • [OpenAI Blog - auto-interp](https://github.com/EleutherAI/sae-auto-interp)\]\[[multimodal-sae](https://github.com/EvolvingLMMs-Lab/multimodal-sae)\]\[[Language-Model-SAEs](https://github.com/OpenMOSS/Language-Model-SAEs)\]\[[SAE-Reasoning](https://github.com/AIRI-Institute/SAE-Reasoning)\]
      • [paper - 7B-Chat)\]
      • [paper
      • [paper - ai/geogalactica)\]\[[sciparser](https://github.com/davendw49/sciparser)\]\[[GeoGPT](https://github.com/GeoGPT-Research-Project/GeoGPT)\]\[[Earth-Agent](https://github.com/opendatalab/Earth-Agent)\]
      • [paper - of-thought-llm)\]\[[SymbCoT](https://github.com/Aiden0526/SymbCoT)\]
      • [paper - coai/CharacterGLM-6B)\]
      • [paper - ai/DeepSeek-Coder-V2)\]\[[DeepSeek-V2.5](https://huggingface.co/deepseek-ai/DeepSeek-V2.5)\]\[[Ling-Coder-lite](https://arxiv.org/abs/2503.17793)\]
      • [paper - 6B](https://github.com/THUDM/ChatGLM-6B)\]\[[ChatGLM2-6B](https://github.com/THUDM/ChatGLM2-6B)\]\[[ChatGLM3](https://github.com/THUDM/ChatGLM3)\]\[[GLM-4](https://github.com/THUDM/GLM-4)\]\[[GLM-4.5V and GLM-4.1V-Thinking](https://github.com/THUDM/GLM-4.1V-Thinking)\]\[[modeling_chatglm.py](https://huggingface.co/THUDM/glm-4-9b-chat/blob/main/modeling_chatglm.py)\]\[[AgentTuning](https://github.com/THUDM/AgentTuning)\]\[[AlignBench](https://github.com/THUDM/AlignBench)\]\[[GLM-Edge](https://github.com/THUDM/GLM-Edge)\]\[[slime](https://github.com/THUDM/slime)\]
      • [paper - 7B-8k](https://huggingface.co/apple/DCLM-7B-8k)\]\[[data-agora](https://github.com/neulab/data-agora)\]\[[Data Selection via Optimal Control for Language Models](https://arxiv.org/abs/2410.07064)\]\[[PreSelect](https://github.com/hkust-nlp/PreSelect)\]\[[DataRater](https://arxiv.org/abs/2505.17895)\]\[[AttentionInfluence](https://arxiv.org/abs/2505.07293)\]
      • [paper - AILab/flash-attention)\]\[[xformers](https://github.com/facebookresearch/xformers)\]\[[SageAttention](https://github.com/thu-ml/SageAttention)\]\[[SpargeAttn](https://github.com/thu-ml/SpargeAttn)\]
      • [paper - deepmind/open_x_embodiment)\]\[[Safari SDK](https://github.com/google-deepmind/gemini-robotics-sdk)\]
      • [paper - juicer)\]
      • [paper - NLPIR/LLM4IR-Survey)\]\[[YuLan-IR](https://github.com/RUC-GSAI/YuLan-IR)\]\[[A Survey of Conversational Search](https://arxiv.org/abs/2410.15576)\]\[[A Survey of Model Architectures in Information Retrieval](https://arxiv.org/abs/2502.14822)\]\[[A Survey of Query Optimization in Large Language Models](https://arxiv.org/abs/2412.17558)\]\[[Improving Generalization in Intent Detection](https://arxiv.org/abs/2504.13592)\]
      • [paper
      • [paper - recommendation)\]\[[Towards An Efficient LLM Training Paradigm for CTR Prediction](https://arxiv.org/abs/2503.01001)\]
      • [paper - Sequence Recommendation Models Need Decoupled Embeddings](https://arxiv.org/abs/2410.02604)\]\[[OneRec](https://arxiv.org/abs/2502.18965)\]\[[OneRec Technical Report](https://arxiv.org/abs/2506.13695)\]\[[OneRec-V2 Technical Report](https://arxiv.org/abs/2508.20900)\]\[[OneSearch](https://arxiv.org/abs/2509.03236)\]\[[MTGR](https://tech.meituan.com/2025/05/19/meituan-generative-recommendation.html)\]\[[MIM](https://arxiv.org/abs/2502.00321)\]\[[URM](https://arxiv.org/abs/2502.03041)\]\[[UniROM](https://arxiv.org/abs/2505.19755)\]\[[RecGPT Technical Report](https://arxiv.org/abs/2507.22879)\]\[[OnePiece](https://arxiv.org/abs/2509.18091)\]
      • [paper
      • [paper
      • [paper - GSAI/YuLan-Chat)\]\[[Yulan-GARDEN](https://github.com/RUC-GSAI/Yulan-GARDEN)\]\[[YuLan-Mini](https://github.com/RUC-GSAI/YuLan-Mini)\]
      • [paper - project/bigcodebench)\]\[[BigCodeArena](https://github.com/bigcode-project/bigcodearena)\]\[[LiveCodeBench](https://github.com/LiveCodeBench/LiveCodeBench)\]\[[evalplus](https://github.com/evalplus/evalplus)\]\[[BigOBench](https://arxiv.org/abs/2503.15242)\]
      • [paper - ailab/persona-hub)\]\[[MAGA](https://arxiv.org/abs/2502.04235)\]\[[BeyondWeb](https://arxiv.org/abs/2508.10975)\]
      • [paper
      • [paper - auto-alignment)\]
      • [paper - NLP/RAG)\]\[[Seven Failure Points When Engineering a Retrieval Augmented Generation System](https://arxiv.org/abs/2401.05856)\]\[[Improving Retrieval Performance in RAG Pipelines with Hybrid Search](https://towardsdatascience.com/improving-retrieval-performance-in-rag-pipelines-with-hybrid-search-c75203c2f2f5)\]\[[15 Advanced RAG Techniques from Pre-Retrieval to Generation](https://www.willowtreeapps.com/guides/advanced-rag-techniques)\]
      • [paper - RAG](https://github.com/microsoft/PIKE-RAG)\]\[[GraphRAG-Local-UI](https://github.com/severian42/GraphRAG-Local-UI)\]\[[nano-graphrag](https://github.com/gusye1234/nano-graphrag)\]\[[fast-graphrag](https://github.com/circlemind-ai/fast-graphrag)\]\[[graph-rag](https://github.com/sarthakrastogi/graph-rag)\]\[[llm-graph-builder](https://github.com/neo4j-labs/llm-graph-builder)\]\[[Triplex](https://huggingface.co/SciPhi/Triplex)\]\[[knowledge_graph_maker](https://github.com/rahulnyk/knowledge_graph_maker)\]\[[itext2kg](https://github.com/AuvaLab/itext2kg)\]\[[KG_RAG](https://github.com/BaranziniLab/KG_RAG)\]
      • [paper
      • [paper
      • [paper - Machine-Learning-Lab/NoteLLM)\]\[[NoteLLM](https://arxiv.org/abs/2403.01744)\]\[[SSD](https://arxiv.org/abs/2107.05204)\]\[[PaRT](https://arxiv.org/abs/2504.20624)\]\[[GenRank](https://arxiv.org/abs/2505.04180)\]\[[UniGRF](https://arxiv.org/abs/2504.16454)\]\[[GAVE](https://arxiv.org/abs/2504.14587)\]
      • [paper
      • [paper - NLP-Group/HippoRAG)\]\[[HippoRAG 2](https://arxiv.org/abs/2502.14802)\]
      • [paper - Agent](https://github.com/QwenLM/Qwen-Agent)\]\[[AutoIF](https://github.com/QwenLM/AutoIF)\]\[[modeling_qwen2.py](https://github.com/huggingface/transformers/blob/main/src/transformers/models/qwen2/modeling_qwen2.py)\]
      • [paper - 1)\]\[[Moto](https://github.com/TencentARC/Moto)\]\[[BridgeVLA](https://github.com/BridgeVLA/BridgeVLA)\]
      • [paper - AILab/flash-attention)\]
      • [blog - llama/llama3)\]\[[llama-models](https://github.com/meta-llama/llama-models)\]\[[llama-recipes](https://github.com/meta-llama/llama-recipes)\]\[[LLM Adaptation](https://ai.meta.com/blog/adapting-large-language-models-llms/)\]\[[Llama-Nemotron: Efficient Reasoning Models](https://arxiv.org/abs/2505.00949)\]\[[llama3-from-scratch](https://github.com/naklecha/llama3-from-scratch)\]\[[nano-llama31](https://github.com/karpathy/nano-llama31)\]\[[minimind](https://github.com/jingyaogong/minimind)\]\[[felafax](https://github.com/felafax/felafax)\]
      • [paper - Shanghai/ICSFSurvey)\]
      • [Prompt4ReasoningPapers
      • [OpenCompass - Eval](https://github.com/open-compass/GAOKAO-Eval)\]\[[VLMEvalKit](https://github.com/open-compass/VLMEvalKit)\]
      • [PEFT - advanced](https://github.com/huggingface/autotrain-advanced)\]\[[accelerate](https://github.com/huggingface/accelerate)\]\[[LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)\]\[[LMFlow](https://github.com/OptimalScale/LMFlow)\]\[[xtuner](https://github.com/InternLM/xtuner)\]\[[MFTCoder](https://github.com/codefuse-ai/MFTCoder)\]\[[llm-foundry](https://github.com/mosaicml/llm-foundry)\]\[[ms-swift](https://github.com/modelscope/ms-swift)\]\[[Liger-Kernel](https://github.com/linkedin/Liger-Kernel)\]\[[MoE-PEFT](https://github.com/TUDB-Labs/MoE-PEFT)\]
      • [LangChain - rag/)\]\[[LangChain Hub](https://smith.langchain.com/hub)\]\[[LangGraph](https://github.com/langchain-ai/langgraph)\]\[[LangGraph 101](https://github.com/langchain-ai/langgraph-101)\]\[[executive-ai-assistant](https://github.com/langchain-ai/executive-ai-assistant)\]
      • [LlamaIndex - llama/llama_deploy)\]\[[A Cheat Sheet and Some Recipes For Building Advanced RAG](https://blog.llamaindex.ai/a-cheat-sheet-and-some-recipes-for-building-advanced-rag-803a9d94c41b)\]\[[Fine-Tuning Embeddings for RAG with Synthetic Data](https://www.llamaindex.ai/blog/fine-tuning-embeddings-for-rag-with-synthetic-data-e534409a3971)\]
      • [AutoGPT - Engineer](https://github.com/gpt-engineer-org/gpt-engineer)\]\[[AgentGPT](https://github.com/reworkd/AgentGPT)\]\[[OpenManus](https://github.com/FoundationAgents/OpenManus)\]\[[owl](https://github.com/camel-ai/owl)\]\[[AgenticSeek](https://github.com/Fosowl/agenticSeek)\]\[[langmanus](https://github.com/langmanus/langmanus)\]\[[DeerFlow](https://github.com/bytedance/deer-flow)\]\[[JoyAgent-JDGenie](https://github.com/jd-opensource/joyagent-jdgenie)\]
      • [LlamaFamily/Llama-Chinese - AI/Chinese-Llama-2-7b](https://github.com/LinkSoul-AI/Chinese-Llama-2-7b)\]\[[llama3-Chinese-chat](https://github.com/CrazyBoyM/llama3-Chinese-chat)\]\[[phi3-Chinese](https://github.com/CrazyBoyM/phi3-Chinese)\]\[[LLM-Chinese](https://github.com/CrazyBoyM/LLM-Chinese)\]\[[Llama3-Chinese-Chat](https://github.com/Shenzhi-Wang/Llama3-Chinese-Chat)\]\[[llama3-chinese](https://github.com/seanzhang-zhichen/llama3-chinese)\]
      • [text-generation-inference - embeddings-inference](https://github.com/huggingface/text-embeddings-inference)\]\[[quantization](https://huggingface.co/docs/transformers/main/en/quantization)\]\[[optimum-quanto](https://github.com/huggingface/optimum-quanto)\]\[[optimum](https://github.com/huggingface/optimum)\]\[[huggingface-inference-toolkit](https://github.com/huggingface/huggingface-inference-toolkit)\]\[[torchao](https://github.com/pytorch/ao)\]
      • [llm-reasoners - groq/g1)\]\[[Open-O1](https://github.com/Open-Source-O1/Open-O1)\]\[[show-me](https://github.com/marlaman/show-me)\]\[[OpenR](https://github.com/openreasoner/openr)\]\[[CoRT](https://github.com/PhialsBasement/Chain-of-Recursive-Thoughts)\]
      • [ChuanhuChatGPT - Next-Web](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web)\]
      • [ray - dev/coze-studio)\]\[[academy](https://github.com/anyscale/academy)\]\[[ant-ray](https://github.com/antgroup/ant-ray)\]\[[dask](https://github.com/dask/dask)\]\[[TaskingAI](https://github.com/TaskingAI/TaskingAI)\]\[[gpt4all](https://github.com/nomic-ai/gpt4all)\]\[[ollama](https://github.com/jmorganca/ollama)\]\[[llama.cpp](https://github.com/ggerganov/llama.cpp)\]\[[mindsdb](https://github.com/mindsdb/mindsdb)\]\[[bisheng](https://github.com/dataelement/bisheng)\]\[[phidata](https://github.com/phidatahq/phidata)\]\[[guidance](https://github.com/guidance-ai/guidance)\]\[[outlines](https://github.com/outlines-dev/outlines)\]\[[jsonformer](https://github.com/1rgs/jsonformer)\]\[[fabric](https://github.com/danielmiessler/fabric)\]\[[mem0](https://github.com/mem0ai/mem0)\]\[[taipy](https://github.com/Avaiga/taipy)\]\[[langflow](https://github.com/langflow-ai/langflow)\]
      • [OpenLLM - llm](https://github.com/mlc-ai/mlc-llm)\]\[[ollama](https://github.com/jmorganca/ollama)\]\[[open-webui](https://github.com/open-webui/open-webui)\]\[[torchchat](https://github.com/pytorch/torchchat)\]
      • [TensorRT-LLM - inference-server/server)\]\[[Dynamo](https://github.com/ai-dynamo/dynamo)\]\[[GenerativeAIExamples](https://github.com/NVIDIA/GenerativeAIExamples)\]\[[TensorRT-Model-Optimizer](https://github.com/NVIDIA/TensorRT-Model-Optimizer)\]\[[TensorRT](https://github.com/NVIDIA/TensorRT)\]\[[kvpress](https://github.com/NVIDIA/kvpress)\]\[[OpenVINO](https://github.com/openvinotoolkit/openvino)\]
      • [BabyAGI
      • [recommenders - algorithm)\]\[[Awesome-RSPapers](https://github.com/RUCAIBox/Awesome-RSPapers)\]\[[RecBole](https://github.com/RUCAIBox/RecBole)\]\[[RecSysDatasets](https://github.com/RUCAIBox/RecSysDatasets)\]\[[LLM4Rec-Awesome-Papers](https://github.com/WLiK/LLM4Rec-Awesome-Papers)\]\[[Awesome-LLM-for-RecSys](https://github.com/CHIANGEL/Awesome-LLM-for-RecSys)\]\[[Awesome-LLM4RS-Papers](https://github.com/nancheng58/Awesome-LLM4RS-Papers)\]\[[DA-CL-4Rec](https://github.com/KingGugu/DA-CL-4Rec)\]\[[ReChorus](https://github.com/THUwangcy/ReChorus)\]\[[Transformers4Rec](https://github.com/NVIDIA-Merlin/Transformers4Rec)\]\[[torchrec](https://github.com/pytorch/torchrec)\]
      • [RedPajama-Data - minigrid-datasets](https://github.com/dunno-lab/xland-minigrid-datasets)\]\[[OmniCorpus](https://github.com/OpenGVLab/OmniCorpus)\]\[[dclm](https://github.com/mlfoundations/dclm)\]\[[Infinity-Instruct](https://github.com/FlagOpen/Infinity-Instruct)\]\[[MNBVC](https://github.com/esbatmop/MNBVC)\]\[[LMSYS-Chat-1M](https://arxiv.org/abs/2309.11998)\]\[[kangas](https://github.com/comet-ml/kangas)\]\[[openwebtext](https://github.com/jcpeterson/openwebtext)\]\[[nlp_chinese_corpus](https://github.com/brightmart/nlp_chinese_corpus)\]\[[open-thoughts](https://github.com/open-thoughts/open-thoughts)\]\[[Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k)\]\[[dolphin-r1](https://huggingface.co/datasets/cognitivecomputations/dolphin-r1)\]
      • [chatgpt-retrieval-plugin - LLM-RAG-Application](https://github.com/lizhe2004/Awesome-LLM-RAG-Application)\]
      • [haystack - Chatchat](https://github.com/chatchat-space/Langchain-Chatchat)\]\[[RAGFlow](https://github.com/infiniflow/ragflow)\]\[[infinity](https://github.com/infiniflow/infinity)\]
      • [paper - SYSU/Embodied_AI_Paper_List)\]
      • [Firefly - chitchat](https://github.com/yangjianxin1/GPT2-chitchat)\]
      • [MOSS - RLHF](https://github.com/OpenLMLab/MOSS-RLHF)\]
      • [translation-agent - zero](https://github.com/frdel/agent-zero)\]\[[AgentK](https://github.com/mikekelly/AgentK)\]\[[evolving-agents](https://github.com/matiasmolinas/evolving-agents)\]\[[EvoAgentX](https://github.com/EvoAgentX/EvoAgentX)\]\[[DGM](https://github.com/jennyzzt/dgm)\]\[[Twitter Personality](https://github.com/wordware-ai/twitter)\]\[[RD-Agent](https://github.com/microsoft/RD-Agent)\]\[[TinyTroupe](https://github.com/microsoft/TinyTroupe)\]\[[Youtu-agent](https://github.com/TencentCloudADP/youtu-agent)\]\[[Hello-Agents](https://github.com/datawhalechina/hello-agents)\]
      • [screenshot-to-code - ai/vanna)\]\[[NL2SQL_Handbook](https://github.com/HKUSTDial/NL2SQL_Handbook)\]\[[TAG-Bench](https://github.com/TAG-Research/TAG-Bench)\]\[[Spider2](https://github.com/xlang-ai/Spider2)\]\[[WrenAI](https://github.com/Canner/WrenAI)\]
      • [cs230-code-examples - template](https://github.com/victoresque/pytorch-template)\]\[[songquanpeng/pytorch-template](https://github.com/songquanpeng/pytorch-template)\]\[[Academic-project-page-template](https://github.com/eliahuhorwitz/Academic-project-page-template)\]\[[WritingAIPaper](https://github.com/hzwer/WritingAIPaper)\]
      • [Megatron-LM - DeepSpeed](https://github.com/deepspeedai/Megatron-DeepSpeed)\]\[[Megatron-DeepSpeed](https://github.com/bigscience-workshop/Megatron-DeepSpeed)\]\[[Pai-Megatron-Patch](https://github.com/alibaba/Pai-Megatron-Patch)\]\[[Megatron-MoE-ModelZoo](https://github.com/yanring/Megatron-MoE-ModelZoo)\]\[[verl_megatron_practice](https://github.com/ISEEKYAN/verl_megatron_practice)\]
      • [LMDeploy - AI/LitServe)\]
      • [evaluate - guidebook](https://github.com/huggingface/evaluation-guidebook)\]\[[EvalScope](https://github.com/modelscope/evalscope)\]\[[LLMPerf](https://github.com/ray-project/llmperf)\]\[[OpenEvals](https://github.com/langchain-ai/openevals)\]\[[DeepEval](https://github.com/confident-ai/deepeval)\]\[[Awesome-LLM-Eval](https://github.com/onejune2018/Awesome-LLM-Eval)\]\[[LLM-eval-survey](https://github.com/MLGroupJLU/LLM-eval-survey)\]\[[llm_benchmarks](https://github.com/leobeeson/llm_benchmarks)\]\[[Awesome-LLMs-Evaluation-Papers](https://github.com/tjunlp-lab/Awesome-LLMs-Evaluation-Papers)\]
      • [lm-evaluation-harness - evals](https://github.com/openai/simple-evals)\]\[[OpenAI Evals](https://evals.openai.com/)\]
      • [AlpacaEval Leaderboard - lab/alpaca_eval)\]
      • [chatgpt-on-wechat - on-wechat](https://github.com/hanfangyuan4396/dify-on-wechat)\]\[[WeClone](https://github.com/xming521/WeClone)\]\[[LLM-As-Chatbot](https://github.com/deep-diver/LLM-As-Chatbot)\]\[[NextChat](https://github.com/ChatGPTNextWeb/NextChat)\]\[[chatbox](https://github.com/Bin-Huang/chatbox)\]\[[cherry-studio](https://github.com/CherryHQ/cherry-studio)\]\[[ChatWise](https://chatwise.app)\]\[[khoj](https://github.com/khoj-ai/khoj)\]\[[HuixiangDou](https://github.com/InternLM/HuixiangDou)\]\[[Streamer-Sales](https://github.com/PeterH0323/Streamer-Sales)\]\[[Tianji](https://github.com/SocialAI-tianji/Tianji)\]\[[metahuman-stream](https://github.com/lipku/metahuman-stream)\]\[[aiavatarkit](https://github.com/uezo/aiavatarkit)\]\[[ai-getting-started](https://github.com/a16z-infra/ai-getting-started)\]\[[chatnio](https://github.com/zmh-program/chatnio)\]\[[VideoChat](https://github.com/Henry-23/VideoChat)\]\[[livetalking](https://github.com/lipku/livetalking)\]
      • [crewAI - llama/llama_deploy)\]\[[gpt-computer-assistant](https://github.com/onuratakan/gpt-computer-assistant)\]\[[agentic_patterns](https://github.com/neural-maze/agentic_patterns)\]\[[pydantic-ai](https://github.com/pydantic/pydantic-ai)\]\[[PocketFlow](https://github.com/The-Pocket/PocketFlow)\]\[[suna](https://github.com/kortix-ai/suna)\]
      • [Awesome-Chinese-LLM - LLMs-In-China](https://github.com/wgwang/awesome-LLMs-In-China)\]\[[awesome-LLM-resourses](https://github.com/WangRongsheng/awesome-LLM-resourses)\]
      • [MiniCPM - MoE](https://github.com/SkyworkAI/Skywork-MoE)\]\[[Orion](https://github.com/OrionStarAI/Orion)\]\[[BELLE](https://github.com/LianjiaTech/BELLE)\]\[[Yuan-2.0](https://github.com/IEIT-Yuan/Yuan-2.0)\]\[[Yuan2.0-M32](https://github.com/IEIT-Yuan/Yuan2.0-M32)\]\[[Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM)\]\[[Index-1.9B](https://github.com/bilibili/Index-1.9B)\]\[[Aquila2](https://github.com/FlagAI-Open/Aquila2)\]
      • [LLM101n - course](https://github.com/mlabonne/llm-course)\]\[[intro-llm](https://intro-llm.github.io/)\]\[[llm-cookbook](https://github.com/datawhalechina/llm-cookbook)\]\[[hugging-llm](https://github.com/datawhalechina/hugging-llm)\]\[[generative-ai-for-beginners](https://github.com/microsoft/generative-ai-for-beginners)\]\[[awesome-generative-ai-guide](https://github.com/aishwaryanr/awesome-generative-ai-guide)\]\[[LLMs-from-scratch](https://github.com/rasbt/LLMs-from-scratch)\]\[[llm-action](https://github.com/liguodongiot/llm-action)\]\[[llms_idx](https://dongnian.icu/llms/llms_idx/)\]\[[tiny-universe](https://github.com/datawhalechina/tiny-universe)\]\[[AISystem](https://github.com/chenzomi12/AISystem)\]
      • [awesome-llm-interpretability - LLM-Interpretability](https://github.com/cooperleong00/Awesome-LLM-Interpretability)\]
      • [functionary - tool-llm](https://github.com/zorazrw/awesome-tool-llm)\]\[[agents-json](https://github.com/wild-card-ai/agents-json)\]\[[langgraph-bigtool](https://github.com/langchain-ai/langgraph-bigtool)\]\[[octotools](https://github.com/octotools/octotools)\]\[[Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)\]
      • [unsloth - ai/oumi)\]\[[VeOmni](https://github.com/ByteDance-Seed/VeOmni)\]\[[Tinker Cookbook](https://github.com/thinking-machines-lab/tinker-cookbook)\]
      • [torchtune
      • [DataTrove - studio](https://github.com/HumanSignal/label-studio)\]\[[autolabel](https://github.com/refuel-ai/autolabel)\]\[[synthetic-data-generator](https://github.com/hitsz-ids/synthetic-data-generator)\]\[[NeMo-Curator](https://github.com/NVIDIA-NeMo/Curator)\]\[[distilabel](https://github.com/argilla-io/distilabel)\]\[[Easy Dataset](https://github.com/ConardLi/easy-dataset)\]\[[text-dedup](https://github.com/ChenghaoMou/text-dedup)\]\[[DataFlow](https://github.com/OpenDCAI/DataFlow)\]\[[GraphGen](https://github.com/open-sciencelab/GraphGen)\]
      • [openfold - pytorch](https://github.com/lucidrains/alphafold3-pytorch)\]\[[alphagenome](https://github.com/lucidrains/alphagenome)\]\[[Protenix](https://github.com/bytedance/Protenix)\]\[[AlphaFold3](https://github.com/kyegomez/AlphaFold3)\]\[[Ligo-Biosciences/AlphaFold3](https://github.com/Ligo-Biosciences/AlphaFold3)\]\[[LucaOne](https://github.com/LucaOne/LucaOne)\]\[[esm](https://github.com/evolutionaryscale/esm)\]\[[AlphaPPImd](https://github.com/AspirinCode/AlphaPPImd)\]\[[visual-med-alpaca](https://github.com/cambridgeltl/visual-med-alpaca)\]\[[chai-lab](https://github.com/chaidiscovery/chai-lab)\]\[[evo](https://github.com/evo-design/evo)\]\[[evo2](https://github.com/ArcInstitute/evo2)\]\[[AIRS](https://github.com/divelab/AIRS)\]\[[OpenBioMed](https://github.com/PharMolix/OpenBioMed)\]\[[BioEmu](https://github.com/microsoft/bioemu)\]\[[Accelerating life sciences research](https://openai.com/index/accelerating-life-sciences-research-with-retro-biosciences/)\]\[[SimpleFold](https://github.com/apple/ml-simplefold)\]
      • [paper
      • [mergekit - models](https://huggingface.co/blog/mlabonne/merge-models)\]\[[Model Merging](https://huggingface.co/collections/osanseviero/model-merging-65097893623330a3a51ead66)\]\[[OpenChatKit](https://github.com/togethercomputer/OpenChatKit)\]
      • [alignment-handbook - Chat](https://github.com/deepspeedai/DeepSpeedExamples/blob/master/applications/DeepSpeed-Chat/README.md)\]\[[OpenRLHF](https://github.com/OpenRLHF/OpenRLHF)\]\[[verl](https://github.com/volcengine/verl)\]\[[AReaL](https://github.com/inclusionAI/AReaL)\]\[[ROLL](https://github.com/alibaba/ROLL)\]\[[Nemo RL](https://github.com/NVIDIA-NeMo/RL)\]\[[RL-Factory](https://github.com/Simple-Efficient/RL-Factory)\]\[[Verifiers](https://github.com/willccbb/verifiers)\]
      • [vimGPT
      • [search_with_lepton - oval/storm)\]\[[searxng](https://github.com/searxng/searxng)\]\[[Perplexica](https://github.com/ItzCrazyKns/Perplexica)\]\[[rag-search](https://github.com/thinkany-ai/rag-search)\]\[[sensei](https://github.com/jjleng/sensei)\]\[[azure-search-openai-demo](https://github.com/Azure-Samples/azure-search-openai-demo)\]\[[Gemini-Search](https://github.com/ammaarreshi/Gemini-Search)\]\[[deep-searcher](https://github.com/zilliztech/deep-searcher)\]
      • [MOSS-RLHF - NLP/OctoThinker)\]\[[limit-of-RLVR](https://arxiv.org/abs/2504.13837)\]\[[Spurious Rewards](https://github.com/ruixin31/Rethink_RLVR)\]\[[ProRL](https://arxiv.org/abs/2505.24864)\]\[[BroRL](https://arxiv.org/abs/2510.01180)\]
      • [gpt-investor - quant](https://github.com/goldmansachs/gs-quant)\]\[[stockbot-on-groq](https://github.com/bklieger-groq/stockbot-on-groq)\]\[[Real-Time-Stock-Market-Prediction-using-Ensemble-DL-and-Rainbow-DQN](https://github.com/THINK989/Real-Time-Stock-Market-Prediction-using-Ensemble-DL-and-Rainbow-DQN)\]\[[openbb-agents](https://github.com/OpenBB-finance/openbb-agents)\]\[[ai-hedge-fund](https://github.com/virattt/ai-hedge-fund)\]\[[A_Share_investment_Agent](https://github.com/24mlight/A_Share_investment_Agent)\]\[[ai-financial-agent](https://github.com/virattt/ai-financial-agent)\]\[[Finance](https://github.com/shashankvemuri/Finance)\]
      • [ragas - community/rageval)\]
      • [QAnything - llm](https://github.com/Mintplex-Labs/anything-llm)\]\[[FastGPT](https://github.com/labring/FastGPT)\]\[[mem0](https://github.com/mem0ai/mem0)\]\[[Memary](https://github.com/kingjulio8238/Memary)\]
      • [alphafold
      • [SearchEngine - labs](https://github.com/elastic/elasticsearch-labs)\]\[[OpenSearch](https://github.com/opensearch-project/OpenSearch)\]\[[HNSWLib](https://github.com/nmslib/hnswlib)\]\[[Tevatron](https://github.com/texttron/tevatron)\]\[[txtai](https://github.com/neuml/txtai)\]
      • [LeRobot - Embodied-AI/Genesis)\]\[[DORA](https://github.com/dora-rs/dora)\]\[[awesome-ai-agents](https://github.com/e2b-dev/awesome-ai-agents)\]\[[IsaacLab](https://github.com/isaac-sim/IsaacLab)\]\[[IsaacGymEnvs](https://github.com/isaac-sim/IsaacGymEnvs)\]\[[OmniIsaacGymEnvs](https://github.com/isaac-sim/OmniIsaacGymEnvs)\]\[[Isaac-GR00T](https://github.com/NVIDIA/Isaac-GR00T)\]\[[Awesome-Robotics-3D](https://github.com/zubair-irshad/Awesome-Robotics-3D)\]\[[AimRT](https://github.com/AimRT/AimRT)\]\[[agibot_x1_train](https://github.com/AgibotTech/agibot_x1_train)\]\[[Agibot-World](https://github.com/OpenDriveLab/Agibot-World)\]\[[unitree_IL_lerobot](https://github.com/unitreerobotics/unitree_IL_lerobot)\]\[[unitree_rl_gym](https://github.com/unitreerobotics/unitree_rl_gym)\]\[[openpi](https://github.com/Physical-Intelligence/openpi)\]
      • [PromptPapers - engineering)\]\[[ChatGPT Prompt Engineering for Developers](https://prompt-engineering.xiniushu.com/)\]\[[Prompt Engineering Guide](https://www.promptingguide.ai/zh)\]\[[k12promptguide](https://www.k12promptguide.com/)\]\[[gpt-prompt-engineer](https://github.com/mshumer/gpt-prompt-engineer)\]\[[awesome-chatgpt-prompts](https://github.com/f/awesome-chatgpt-prompts)\]\[[awesome-chatgpt-prompts-zh](https://github.com/PlexPt/awesome-chatgpt-prompts-zh)\]\[[Prompt_Engineering](https://github.com/NirDiamant/Prompt_Engineering)\]\[[system-prompts-and-models-of-ai-tools](https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools)\]\[[System Prompts Leaks](https://github.com/asgeirtj/system_prompts_leaks)\]\[[leaked-system-prompts](https://github.com/jujumilk3/leaked-system-prompts)\]\[[CL4R1T4S](https://github.com/elder-plinius/CL4R1T4S)\]\[[Anthropic System Prompts](https://docs.anthropic.com/en/release-notes/system-prompts)\]\[[Prompt engineering overview](https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview)\]\[[GPT-5 prompting guide](https://cookbook.openai.com/examples/gpt-5/gpt-5_prompting_guide)\]
      • [wandb
      • [BCEmbedding - embedding-base_v1](https://huggingface.co/maidalun1020/bce-embedding-base_v1)\]\[[bce-reranker-base_v1](https://huggingface.co/maidalun1020/bce-reranker-base_v1)\]
      • [llm-datasets - LLM-Synthetic-Data](https://github.com/wasiahmad/Awesome-LLM-Synthetic-Data)\]\[[Detecting Pretraining Data](https://github.com/swj0419/detect-pretrain-code)\]
      • [PDF-Extract-Kit - tech/colpali)\]\[[localGPT-Vision](https://github.com/PromtEngineer/localGPT-Vision)\]\[[mPLUG-DocOwl](https://github.com/X-PLUG/mPLUG-DocOwl)\]\[[nv-ingest](https://github.com/NVIDIA/nv-ingest)\]\[[Dolphin](https://github.com/bytedance/Dolphin)\]
      • [Skywork - MoE](https://github.com/SkyworkAI/Skywork-MoE)\]\[[Orion](https://github.com/OrionStarAI/Orion)\]\[[BELLE](https://github.com/LianjiaTech/BELLE)\]\[[Yuan-2.0](https://github.com/IEIT-Yuan/Yuan-2.0)\]\[[Yuan2.0-M32](https://github.com/IEIT-Yuan/Yuan2.0-M32)\]\[[Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM)\]\[[Index-1.9B](https://github.com/bilibili/Index-1.9B)\]\[[dots.llm1](https://github.com/rednote-hilab/dots.llm1)\]\[[Aquila2](https://github.com/FlagAI-Open/Aquila2)\]
      • [Awesome-Scientific-Language-Models - husky/gpt_academic)\]\[[ChatPaper](https://github.com/kaixindelele/ChatPaper)\]\[[scispacy](https://github.com/allenai/scispacy)\]\[[awesome-ai4s](https://github.com/hyperai/awesome-ai4s)\]\[[xVal](https://github.com/PolymathicAI/xVal)\]
      • [llama-moe - pytorch](https://github.com/lucidrains/PEER-pytorch)\]\[[GRIN-MoE](https://github.com/microsoft/GRIN-MoE)\]\[[MoE-plus-plus](https://github.com/SkyworkAI/MoE-plus-plus)\]\[[MoH](https://github.com/SkyworkAI/MoH)\]\[[MoE-PEFT](https://github.com/TUDB-Labs/MoE-PEFT)\]\[[Cortex](https://github.com/qibin0506/Cortex)\]
      • [llm-colosseum - org/GamingAgent)\]\[[UltraEval](https://github.com/OpenBMB/UltraEval)\]\[[Humanity's Last Exam](https://github.com/centerforaisafety/hle)\]
      • [paper - ai/Mooncake)\]\[[ktransformers](https://github.com/kvcache-ai/ktransformers)\]
      • [paper - Torch](https://github.com/shenweichen/DeepCTR-Torch)\]\[[pytorch-mmoe](https://github.com/ZhichenZhao/pytorch-mmoe)\]
      • [paper - Augmented Generation with Graphs](https://arxiv.org/abs/2501.00309)\]\[[code](https://github.com/Graph-RAG/GraphRAG)\]\[[Awesome-GraphRAG](https://github.com/DEEP-PolyU/Awesome-GraphRAG)\]
      • [paper
      • [paper - cite](https://github.com/MadryLab/context-cite)\]\[[OmniThink](https://github.com/zjunlp/OmniThink)\]\[[SelfCite](https://arxiv.org/abs/2502.09604)\]\[[LLMxMapReduce](https://github.com/thunlp/LLMxMapReduce)\]\[[WriteHERE](https://github.com/principia-ai/WriteHERE)\]\[[LongWriter-Zero](https://arxiv.org/abs/2506.18841)\]
      • [paper - Augmented Generation: A Survey](https://arxiv.org/abs/2405.07437)\]\[[Ragas](https://github.com/explodinggradients/ragas)\]\[[RAGChecker](https://github.com/amazon-science/RAGChecker)\]\[[rageval](https://github.com/gomate-community/rageval)\]\[[CORAL](https://github.com/Ariya12138/CORAL)\]\[[WebWalker](https://github.com/Alibaba-NLP/WebWalker)\]\[[Open RAG Eval](https://github.com/vectara/open-rag-eval)\]
      • [Yi-Coder - 7B](https://github.com/aixcoder-plugin/aiXcoder-7B)\]\[[codealpaca](https://github.com/sahil280114/codealpaca)\]
      • [paper - Paper-List)\]\[[Challenges and Paths Towards AI for Software Engineering](https://arxiv.org/abs/2503.22625)\]
      • [paper
      • [paper - MCTS](https://github.com/DIRECT-BIT/SRA-MCTS)\]
      • [paper
      • [paper - Researcher)\]
      • [paper - Coder)\]\[[CodeArena](https://arxiv.org/abs/2412.05210)\]\[[CodeElo](https://arxiv.org/abs/2501.01257)\]
      • [fun-rec - RecommenderSystem](https://github.com/zhongqiangwu960812/AI-RecommenderSystem)\]\[[RecSysPapers](https://github.com/tangxyw/RecSysPapers)\]\[[Algorithm-Practice-in-Industry](https://github.com/Doragd/Algorithm-Practice-in-Industry)\]\[[AlgoNotes](https://github.com/shenweichen/AlgoNotes)\]\[[torch-rechub](https://github.com/datawhalechina/torch-rechub)\]
      • [similarities - dev/leettools)\]
      • [paper
      • [paper - mll/jiant)\]
      • [paper - 4](https://huggingface.co/collections/microsoft/phi-4-677e9380e514feb5577a40e4)\]\[[SmolLM](https://huggingface.co/blog/smollm)\]\[[SmolLM2](https://arxiv.org/abs/2502.02737)\]\[[SmolVLM](https://arxiv.org/abs/2504.05299)\]\[[Computational Bottlenecks of Training Small-scale Large Language Models](https://arxiv.org/abs/2410.19456)\]\[[SLMs-Survey](https://github.com/FairyFali/SLMs-Survey)\]\[[MiniLLM](https://arxiv.org/abs/2306.08543)\]\[[aligning_tinystories](https://philliphaeusler.com/posts/aligning_tinystories/)\]\[[The Smol Training Playbook](https://huggingface.co/spaces/HuggingFaceTB/smol-playbook-toc)\]
      • [tokenizer_summary - Tokenizer](https://github.com/NVIDIA/Cosmos-Tokenizer)\]\[[tiktokenizer](https://github.com/dqbd/tiktokenizer)\]
      • [paper
      • [paper - deepmind/gemma](https://github.com/google-deepmind/gemma)\]\[[gemma.cpp](https://github.com/google/gemma.cpp)\]\[[model](https://ai.google.dev/gemma)\]\[[paligemma](https://github.com/google-research/big_vision/tree/main/big_vision/configs/proj/paligemma)\]\[[gemma-cookbook](https://github.com/google-gemini/gemma-cookbook)\]
      • [paper - gemma-2/)\]\[[Advancing Responsible AI with Gemma](https://developers.googleblog.com/en/smaller-safer-more-transparent-advancing-responsible-ai-with-gemma/)\]\[[Gemma Scope](https://arxiv.org/abs/2408.05147)\]\[[ShieldGemma](https://arxiv.org/abs/2407.21772)\]\[[Gemma-2-9B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Gemma-2-9B-Chinese-Chat)\]
      • [paper - watermarking)\]\[[MarkLLM](https://github.com/THU-BPM/MarkLLM)\]\[[Watermarked_LLM_Identification](https://github.com/THU-BPM/Watermarked_LLM_Identification)\]\[[Awesome-LLM-Watermark](https://github.com/hzy312/Awesome-LLM-Watermark)\]
      • [paper - wpy/SeqXGPT)\]\[[llm-detect-ai](https://github.com/yanqiangmiffy/llm-detect-ai)\]\[[detect-gpt](https://github.com/eric-mitchell/detect-gpt)\]\[[fast-detect-gpt](https://github.com/baoguangsheng/fast-detect-gpt)\]\[[ImBD](https://github.com/Jiaqi-Chen-00/ImBD)\]\[[MAGE](https://github.com/yafuly/MAGE)\]
      • [paper - llm/automix)\]
      • [paper - Copilot/OS-Copilot)\]\[[OS-Atlas](https://github.com/OS-Copilot/OS-Atlas)\]\[[OS-Genesis](https://github.com/OS-Copilot/OS-Genesis)\]\[[SeeClick](https://github.com/njucckevin/SeeClick)\]\[[WindowsAgentArena](https://github.com/microsoft/WindowsAgentArena)\]
      • [paper - ai/DB-GPT)\]\[[DocsGPT](https://github.com/arc53/DocsGPT)\]\[[privateGPT](https://github.com/imartinez/privateGPT)\]\[[localGPT](https://github.com/PromtEngineer/localGPT)\]
      • [paper
      • [paper
      • [paper
      • [paper - Role-Play-Papers)\]\[[RPBench-Auto](https://boson.ai/rpbench-blog/)\]\[[Hermes 3 Technical Report](https://arxiv.org/abs/2408.11857)\]\[[From Persona to Personalization: A Survey on Role-Playing Language Agents](https://arxiv.org/abs/2404.18231)\]\[[MMRole](https://github.com/YanqiDai/MMRole)\]\[[OpenCharacter](https://arxiv.org/abs/2501.15427)\]
      • [blog
      • [paper - Shanghai/CTGSurvey)\]\[[guidance](https://github.com/guidance-ai/guidance)\]\[[outlines](https://github.com/outlines-dev/outlines)\]\[[instructor](https://github.com/instructor-ai/instructor)\]\[[marvin](https://github.com/PrefectHQ/marvin)\]\[[json_repair](https://github.com/mangiucugna/json_repair)\]
      • [paper
      • [paper
      • [paper
      • [paper - agent/digirl)\]\[[Android-Lab](https://github.com/THUDM/Android-Lab)\]\[[AppAgentX](https://github.com/Westlake-AGI-Lab/AppAgentX)\]\[[AgentCPM-GUI](https://github.com/OpenBMB/AgentCPM-GUI)\]
      • [paper - PLUG/MobileAgent)\]\[[Mobile-Agent-v2](https://arxiv.org/abs/2406.01014)\]\[[Mobile-Agent-v3](https://arxiv.org/abs/2508.15144)\]\[[LiMAC](https://arxiv.org/abs/2410.17883)\]\[[Mobile-Agent-E](https://arxiv.org/abs/2501.11733)\]\[[Mobile-Agent-V](https://arxiv.org/abs/2502.17110)\]\[[PC-Agent](https://arxiv.org/abs/2502.14282)\]\[[UI-S1](https://arxiv.org/abs/2509.11543)\]\[[mobile-use](https://github.com/minitap-ai/mobile-use)\]
      • [paper
      • [paper
      • [paper
      • [paper
      • [paper - ai/agentscope)\]\[[modelscope-agent](https://github.com/modelscope/ms-agent)\]
      • [paper
      • [paper - agent](https://github.com/andrewyng/translation-agent)\]
      • [paper - zero)\]\[[AgentK](https://github.com/mikekelly/AgentK)\]\[[AFlow](https://github.com/FoundationAgents/AFlow)\]\[[syftr](https://github.com/datarobot/syftr)\]\[[ASI-Arch](https://github.com/GAIR-NLP/ASI-Arch)\]
      • [blog - robotics-brings-ai-into-the-physical-world)\]
      • [paper
      • [paper - aloha)\]\[[Hardware Code](https://github.com/MarkFzp/mobile-aloha)\]\[[Learning Code](https://github.com/MarkFzp/act-plus-plus)\]\[[UMI](https://github.com/real-stanford/universal_manipulation_interface)\]\[[humanplus](https://github.com/MarkFzp/humanplus)\]\[[TeleVision](https://github.com/OpenTeleVision/TeleVision)\]\[[Surgical Robot Transformer](https://surgical-robot-transformer.github.io/)\]\[[lifelike-agility-and-play](https://github.com/Tencent-RoboticsX/lifelike-agility-and-play)\]\[[ReKep](https://rekep-robot.github.io/)\]\[[Open_Duck_Mini](https://github.com/apirrone/Open_Duck_Mini)\]\[[Learning Visual Parkour from Generated Images](https://lucidsim.github.io/)\]\[[ASAP](https://github.com/LeCAR-Lab/ASAP)\]\[[UniAct](https://github.com/2toinf/UniAct)\]\[[CogACT](https://github.com/microsoft/CogACT)\]\[[Berkeley-Humanoid-Lite](https://github.com/HybridRobotics/Berkeley-Humanoid-Lite)\]
      • [paper
      • [blog
      • [paper - ZJU/Scientific-LLM-Survey)\]\[[sciknoweval](https://github.com/hicai-zju/sciknoweval)\]
      • [paper - research/scFoundation)\]
      • [paper
      • [paper - oval/storm)\]\[[Co-STORM EMNLP 2024](https://www.arxiv.org/abs/2408.15232)\]\[[WikiChat](https://github.com/stanford-oval/WikiChat)\]\[[kiroku](https://github.com/cnunescoelho/kiroku)\]\[[gpt-researcher](https://github.com/assafelovic/gpt-researcher)\]\[[OmniThink](https://github.com/zjunlp/OmniThink)\]
      • [paper - sea/sea)\]\[[AgentReview](https://github.com/Ahren09/AgentReview)\]\[[Researcher](https://github.com/zhu-minjun/Researcher)\]
      • [paper - NLP/OpenResearcher)\]\[[Paper Copilot](https://arxiv.org/abs/2409.04593)\]\[[SciAgentsDiscovery](https://github.com/lamm-mit/SciAgentsDiscovery)\]\[[paper-qa](https://github.com/Future-House/paper-qa)\]\[[GraphReasoning](https://github.com/lamm-mit/GraphReasoning)\]
      • [paper - Scientist)\]\[[AI-Scientist-v2](https://github.com/SakanaAI/AI-Scientist-v2)\]\[[AI-Scientist-ICLR2025-Workshop-Experiment](https://github.com/SakanaAI/AI-Scientist-ICLR2025-Workshop-Experiment)\]\[[Zochi Technical Report](https://www.intology.ai/blog/zochi-tech-report)\]\[[hypothesis-generation](https://github.com/ChicagoHAI/hypothesis-generation)\]\[[Towards an AI co-scientist](https://arxiv.org/abs/2502.18864)\]\[[CodeScientist](https://github.com/allenai/codescientist)\]\[[TinyScientist](https://github.com/ulab-uiuc/tiny-scientist)\]\[[research-town](https://github.com/ulab-uiuc/research-town)\]\[[CMBAgent](https://github.com/CMBAgents/cmbagent)\]\[[Robin](https://github.com/Future-House/robin)\]\[[NovelSeek](https://arxiv.org/abs/2505.16938)\]\[[ToolUniverse](https://github.com/mims-harvard/ToolUniverse)\]
      • [link
      • [paper
      • [paper - ai/AlphaCodium)\]\[[pr-agent](https://github.com/Codium-ai/pr-agent)\]\[[cover-agent](https://github.com/Codium-ai/cover-agent)\]
      • [paper
      • [paper - Hands-AI/OpenHands)\]\[[open-operator](https://github.com/All-Hands-AI/open-operator)\]\[[potpie](https://github.com/potpie-ai/potpie)\]\[[Code Graph Model](https://arxiv.org/abs/2505.16901)\]
      • [paper
      • [paper
      • [paper - 3846.12832)\]\[[code](https://github.com/yya518/FinBERT)\]\[[finBERT](https://github.com/ProsusAI/finBERT)\]\[[valuesimplex/FinBERT](https://github.com/valuesimplex/FinBERT)\]
      • [paper - Foundation/FinRobot)\]
      • [paper - Foundation/FinRL-Meta)\]
      • [paper - FinAI/PIXIU)\]
      • [paper - table-survey](https://github.com/godaai/llm-table-survey)\]\[[table-transformer](https://github.com/microsoft/table-transformer)\]\[[Awesome-Tabular-LLMs](https://github.com/SpursGoZmy/Awesome-Tabular-LLMs)\]\[[Awesome-LLM-Tabular](https://github.com/johnnyhwu/Awesome-LLM-Tabular)\]\[[Tabular-Survey](https://github.com/LAMDA-Tabular/Tabular-Survey)\]\[[Table-LLaVA](https://github.com/SpursGoZmy/Table-LLaVA)\]\[[tablegpt-agent](https://github.com/tablegpt/tablegpt-agent)\]\[[TabSTAR](https://arxiv.org/abs/2505.18125)\]\[[TableLLM](https://github.com/RUCKBReasoning/TableLLM)\]\[[Table-R1](https://github.com/Table-R1/Table-R1)\]\[[OmniSQL](https://github.com/RUCKBReasoning/OmniSQL)\]\[[ChartVLM](https://github.com/UniModal4Reasoning/ChartVLM)\]\[[OmniCaptioner](https://github.com/Alpha-Innovator/OmniCaptioner)\]
      • [paper - team/rllm)\]
      • [paper - Copilot)\]
      • [paper
      • [paper
      • [paper
      • [paper - datasets](https://github.com/virattt/financial-datasets)\]\[[LLMs-in-Finance](https://github.com/hananedupouy/LLMs-in-Finance)\]
      • [paper
      • [paper - Touchstone](https://github.com/IDEA-FinAI/Golden-Touchstone)\]\[[financebench](https://github.com/patronus-ai/financebench)\]\[[OmniEval](https://github.com/RUC-NLPIR/OmniEval)\]\[[FLAME](https://github.com/FLAME-ruc/FLAME)\]\[[FinEval](https://github.com/SUFE-AIFLM-Lab/FinEval)\]\[[CFBenchmark](https://github.com/TongjiFinLab/CFBenchmark)\]\[[MME-Finance](https://github.com/HiThink-Research/MME-Finance)\]\[[BizFinBench](https://github.com/HiThink-Research/BizFinBench)\]\[[MultiFinBen](https://arxiv.org/abs/2506.14028)\]\[[FinSearchComp](https://arxiv.org/abs/2509.13160)\]\[[StockBench](https://github.com/ChenYXxxx/stockbench)\]
      • [paper - sim](https://github.com/ZhuiyiTechnology/roformer-sim)\]
      • [paper - futuredata/ColBERT)\]\[[RAGatouille](https://github.com/AnswerDotAI/RAGatouille)\]\[[rerankers](https://github.com/AnswerDotAI/rerankers)\]\[[Rankify](https://github.com/DataScienceUIBK/Rankify)\]\[[A Reproducibility Study of PLAID](https://arxiv.org/abs/2404.14989)\]\[[Jina-ColBERT-v2](https://arxiv.org/abs/2408.16672)\]
      • [paper - louis/xm-retrievers)\]\[[model](https://huggingface.co/antoinelouis/colbert-xm)\]
      • [paper
      • [paper - LLM4IE-Papers)\]\[[UIE](https://github.com/universal-ie/UIE)\]\[[NERRE](https://github.com/LBNLP/NERRE)\]\[[uie_pytorch](https://github.com/HUSTAI/uie_pytorch)\]
      • [paper
      • [paper
      • [paper - ai/D2LLM)\]
      • [paper
      • [paper - NLP/WebWalker)\]
      • [paper
      • [link
      • [link
      • [paper - LM/Xwin-LM/tree/main/Xwin-Math)\]
      • [paper - Math)\]
      • [paper - Math-Reasoning/Super_MARIO)\]
      • [paper
      • [paper - Berry](https://arxiv.org/abs/2410.02884)\]
      • [paper - LLaVA)\]
      • [paper - Math/We-Math)\]\[[We-Math2.0](https://github.com/We-Math/We-Math2.0)\]\[[URSA](https://arxiv.org/abs/2501.04686)\]
      • [paper
      • [paper - Math)\]\[[Qwen2.5-Math-Demo](https://huggingface.co/spaces/Qwen/Qwen2.5-Math-Demo)\]\[[ProcessBench](https://github.com/QwenLM/ProcessBench)\]\[[SuperCorrect-llm](https://github.com/YangLing0818/SuperCorrect-llm)\]\[[The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://arxiv.org/abs/2501.07301)\]\[[Confucius3-Math](https://github.com/netease-youdao/Confucius3-Math)\]
      • [Numina 1st Place Solution - numina/aimo-progress-prize](https://github.com/project-numina/aimo-progress-prize)\]\[[How NuminaMath Won the 1st AIMO Progress Prize](https://huggingface.co/blog/winning-aimo-progress-prize)\]\[[NuminaMath-7B-TIR](https://huggingface.co/AI-MO/NuminaMath-7B-TIR)\]\[[AI achieves silver-medal standard solving International Mathematical Olympiad problems](https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/)\]\[[Gemini with Deep Think](https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/)\]\[[Gemini 2.5 Deep Think](https://blog.google/products/gemini/gemini-2-5-deep-think/)\]\[[IMO 2025 Problem Solver](https://github.com/lyang36/IMO25)\]\[[AWorld](https://github.com/inclusionAI/AWorld)\]
      • [paper
      • [paper - PaLM)\]
      • [paper - pytorch](https://github.com/lucidrains/AMIE-pytorch)\]
      • [paper
      • [paper
      • [paper - yuexi/AgentCourt)\]
      • [paper - deeplearning](https://github.com/alibaba/x-deeplearning)\]
      • [paper - SSLRec-Papers](https://github.com/HKUDS/Awesome-SSLRec-Papers)\]
      • [paper - recsys/generative-recommenders)\]\[[ExFM](https://arxiv.org/abs/2502.17494)\]\[[KuaiFormer](https://arxiv.org/abs/2411.10057)\]\[[Transformers4Rec](https://github.com/NVIDIA-Merlin/Transformers4Rec)\]\[[TorchRec](https://github.com/meta-pytorch/torchrec)\]\[[LlamaRec](https://github.com/Yueeeeeeee/LlamaRec)\]\[[RecIS](https://github.com/alibaba/RecIS)\]
      • [paper - Tool-Survey)\]
      • [paper
      • [paper
      • [paper - trial-and-error)\]
      • [paper - Bank](https://arxiv.org/abs/2304.08244)\]\[[ToolHop](https://arxiv.org/abs/2501.02506)\]\[[ComplexFuncBench](https://github.com/THUDM/ComplexFuncBench)\]\[[tool-retrieval-benchmark](https://github.com/mangopy/tool-retrieval-benchmark)\]
      • [paper
      • [paper - Wang/ToolGen)\]
      • [blog - Scale Playbook](https://huggingface.co/spaces/nanotron/ultrascale-playbook)\]
      • [blog - architecture-blogpost-encoders-prefixlm-denoising)\]\[[New LLM Pre-training and Post-training Paradigms](https://magazine.sebastianraschka.com/p/new-llm-pre-training-and-post-training)\]
      • [Awesome-LLM-System-Papers - production-llm](https://github.com/jihoo-kim/awesome-production-llm)\]\[[Awesome-MLSys-Blogger](https://mlsys-learner-resources.github.io/Awesome-MLSys-Blogger)\]\[[Awesome-ML-SYS-Tutorial](https://github.com/zhaochenyang20/Awesome-ML-SYS-Tutorial)\]\[[how-to-learn-deep-learning-framework](https://github.com/BBuf/how-to-learn-deep-learning-framework)\]\[[PKU-DAIR/Starter-Guide](https://github.com/PKU-DAIR/Starter-Guide/tree/main/docs/systems)\]\[[open-infra-index](https://github.com/deepseek-ai/open-infra-index)\]\[[CutlassAcademy](https://github.com/MekkCyber/CutlassAcademy)\]\[[Triton-Puzzles](https://github.com/srush/Triton-Puzzles)\]\[[CUDA-Learn-Notes](https://github.com/xlite-dev/CUDA-Learn-Notes)\]\[[AIInfra](https://github.com/Infrasys-AI/AIInfra)\]
      • [paper - Infer](https://arxiv.org/abs/2504.02263)\]\[[MegaScale-MoE](https://arxiv.org/abs/2505.11432)\]\[[DistTrain](https://arxiv.org/abs/2408.04275)\]\[[InfiniteHBD](https://arxiv.org/abs/2502.03885)\]\[[blog](https://www.semianalysis.com/p/100000-h100-clusters-power-network)\]\[[Parameter Server OSDI 2014](https://www.usenix.org/system/files/conference/osdi14/osdi14-paper-li_mu.pdf)\]\[[ps-lite](https://github.com/dmlc/ps-lite)\]\[[ByteCheckpoint](https://arxiv.org/abs/2407.20143)\]\[[HybridFlow](https://arxiv.org/abs/2409.19256)\]\[[ByteRobust](https://arxiv.org/abs/2509.16293)\]
      • [paper
      • [paper
      • [paper
      • [paper - 101B)\]\[[Tele-FLM](https://huggingface.co/CofeAI/Tele-FLM)\]
      • [paper - language-RL](https://github.com/waterhorse1/Natural-language-RL)\]
      • [paper - ye/OpenFedLLM)\]
      • [paper - ai/MergeKit)\]\[[DistillKit](https://github.com/arcee-ai/DistillKit)\]\[[A Survey on Collaborative Strategies in the Era of Large Language Models](https://arxiv.org/abs/2407.06089)\]\[[Model Merging Survey](https://arxiv.org/abs/2408.07666)\]\[[FuseAI](https://github.com/fanqiwan/FuseAI)\]\[[MergeLM](https://github.com/yule-BUAA/MergeLM)\]\[[Long-to-Short-via-Model-Merging](https://github.com/hahahawu/Long-to-Short-via-Model-Merging)\]\[[Model Merging in Pre-training](https://arxiv.org/abs/2505.12082)\]
      • [paper - ConvAI/tree/main/Awesome-Self-Evolution-of-LLM)\]\[[Awesome-Self-Evolving-Agents](https://github.com/EvoAgentX/Awesome-Self-Evolving-Agents)\]
      • [paper - mini)\]\[[Adam](https://arxiv.org/abs/1412.6980)\]\[[AdamW](https://arxiv.org/abs/1711.05101)\]\[[Muon](https://github.com/KellerJordan/Muon)\]
      • [paper - sys/routellm)\]\[[RouterDC](https://github.com/shuhao02/RouterDC)\]\[[masrouter](https://github.com/yanweiyue/masrouter)\]\[[RouterEval](https://github.com/MilkThink-Lab/RouterEval)\]\[[Arch-Router](https://arxiv.org/abs/2506.16655)\]\[[AvengersPro](https://github.com/ZhangYiqun018/AvengersPro)\]\[[Router-R1](https://github.com/ulab-uiuc/Router-R1)\]
      • [paper
      • [paper - ai/OpenDiLoCo)\]\[[Prime](https://github.com/PrimeIntellect-ai/Prime)\]\[[DiLoCo](https://arxiv.org/abs/2311.08105)\]\[[DisTrO](https://github.com/NousResearch/DisTrO)\]\[[Streaming DiLoCo](https://arxiv.org/abs/2501.18512)\]\[[Eager Updates For Overlapped Communication and Computation in DiLoCo](https://arxiv.org/abs/2502.12996)\]\[[Scaling Laws for DiLoCo](https://arxiv.org/abs/2503.09799)\]
      • [paper - piexl/JailbreakZoo)\]\[[jailbreak_llms](https://github.com/verazuo/jailbreak_llms)\]\[[llm-attacks](https://github.com/llm-attacks/llm-attacks)\]\[[Awesome-Jailbreak-on-LLMs](https://github.com/yueliu1999/Awesome-Jailbreak-on-LLMs)\]\[[Constitutional Classifiers](https://arxiv.org/abs/2501.18837)\]
      • [paper - platform)\]\[[open-infra-index](https://github.com/deepseek-ai/open-infra-index)\]\[[Parameter Server OSDI 2014](https://www.usenix.org/system/files/conference/osdi14/osdi14-paper-li_mu.pdf)\]\[[ps-lite](https://github.com/dmlc/ps-lite)\]
      • [paper
      • [paper
      • [paper - LLM-preference-learning)\]
      • [paper - nlp/deita)\]\[[Data-Whisperer](https://github.com/gszfwsb/Data-Whisperer)\]\[[LESS](https://github.com/princeton-nlp/LESS)\]
      • [paper - align/magpie)\]\[[Condor](https://arxiv.org/abs/2501.12273)\]\[[GraphGen](https://github.com/open-sciencelab/GraphGen)\]
      • [paper
      • [paper - Reward-Modeling](https://github.com/RLHFlow/RLHF-Reward-Modeling)\]\[[Online-RLHF](https://github.com/RLHFlow/Online-RLHF)\]\[[Online-DPO-R1](https://github.com/RLHFlow/Online-DPO-R1)\]\[[Minimal-RL](https://github.com/RLHFlow/Minimal-RL)\]\[[Reinforce-Ada](https://github.com/RLHFlow/Reinforce-Ada)\]
      • [paper - M](https://github.com/OpenRLHF/OpenRLHF-M)\]\[[Unraveling RLHF and Its Variants](https://hijkzzz.notion.site/unraveling-rlhf-and-its-variants-engineering-insights)\]\[[Does RLHF Scale](https://arxiv.org/abs/2412.06000)\]
      • [paper - level-Direct-Preference-Optimization)\]\[[Step-DPO](https://github.com/dvlab-research/Step-DPO)\]\[[FineGrainedRLHF](https://github.com/allenai/FineGrainedRLHF)\]\[[MCTS-DPO](https://github.com/YuxiXie/MCTS-DPO)\]\[[Critical Tokens Matter](https://arxiv.org/abs/2411.19943)\]
      • [paper - nlp/SimPO)\]
      • [paper
      • [paper - pytorch](https://github.com/lucidrains/CALM-pytorch)\]
      • [paper - Aligner)\]\[[Nemo RL](https://github.com/NVIDIA-NeMo/RL)\]\[[Long-RL](https://github.com/NVlabs/Long-RL)\]\[[NeMo-Curator](https://github.com/NVIDIA-NeMo/Curator)\]\[[Nemotron-4 340B Technical Report](https://d1qx31qr3h6wln.cloudfront.net/publications/Nemotron_4_340B_8T.pdf)\]\[[Mistral NeMo](https://mistral.ai/news/mistral-nemo/)\]\[[SparseLLM](https://github.com/BaiTheBest/SparseLLM)\]\[[MaskLLM](https://github.com/NVlabs/MaskLLM)\]\[[HelpSteer2-Preference](https://arxiv.org/abs/2410.01257)\]
      • [paper - LM/Xwin-LM)\]
      • [blog
      • [blog - verifier-games-improve-legibility-of-llm-outputs/legibility.pdf)\]
      • [blog - rbr-code-and-data)\]
      • [paper - Self-Guide)\]\[[prompt2model](https://github.com/neulab/prompt2model)\]
      • [paper - memory-transformer/tree/aaai24)\]\[[LM-RMT](https://github.com/booydar/LM-RMT)\]
      • [paper - Infinite](https://arxiv.org/abs/2308.16137)\]
      • [paper
      • [paper - LLM-Long-Context-Modeling](https://github.com/Xnhyacinth/Awesome-LLM-Long-Context-Modeling)\]
      • [paper - nlp/CEPE)\]
      • [paper
      • [paper - V2](https://arxiv.org/abs/2509.24663)\]
      • [paper
      • [paper
      • [paper
      • [paper - granite/granite-code-models)\]\[[granite-3.1-language-models](https://github.com/ibm-granite/granite-3.1-language-models)\]
      • [blog
      • [blog - token-context-windows)\]
      • [blog
      • [paper - pile](https://github.com/EleutherAI/the-pile)\]\[[The Common Pile v0.1](https://arxiv.org/abs/2506.05209)\]\[[ChineseWebText-2.0](https://github.com/CASIA-LM/ChineseWebText-2.0)\]
      • [paper
      • [paper - dev/datadreamer)\]
      • [paper - Tan-dmml/LLM4Annotation)\]
      • [paper - sg/regmix)\]\[[CLIMB](https://arxiv.org/abs/2504.13161)\]\[[QuaDMix](https://arxiv.org/abs/2504.16511)\]\[[Scaling Laws for Optimal Data Mixtures](https://arxiv.org/abs/2507.09404)\]
      • [paper - 2)\]\[[blogpost](https://huggingface.co/spaces/HuggingFaceFW/blogpost-fineweb-v1)\]\[[fineweb](https://huggingface.co/datasets/HuggingFaceFW/fineweb)\]\[[fineweb-edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu)\]\[[FineWeb2](https://arxiv.org/abs/2506.20920)\]\[[Ultra-FineWeb](https://arxiv.org/abs/2505.05427)\]\[[Essential-Web v1.0](https://arxiv.org/abs/2506.14111)\]\[[FinePDFs](https://github.com/huggingface/finepdfs)\]
      • [Awesome-LLM-Eval - eval-survey](https://github.com/MLGroupJLU/LLM-eval-survey)\]\[[llm_benchmarks](https://github.com/leobeeson/llm_benchmarks)\]\[[Awesome-LLMs-Evaluation-Papers](https://github.com/tjunlp-lab/Awesome-LLMs-Evaluation-Papers)\]
      • [paper - RAG](https://github.com/CLUEbenchmark/SuperCLUE-RAG)\]
      • [paper - Benchmark/CMMMU)\]
      • [paper
      • [paper - eval/prometheus-eval)\]\[[prometheus](https://github.com/prometheus-eval/prometheus)\]\[[prometheus-vision](https://github.com/prometheus-eval/prometheus-vision)\]
      • [paper - Lab/lmms-eval)\]\[[VLMEvalKit](https://github.com/open-compass/VLMEvalKit)\]\[[VideoMMMU](https://github.com/EvolvingLMMs-Lab/VideoMMMU)\]
      • [paper - Benchmark/MMMU)\]
      • [blog - leaderboard](https://github.com/vectara/hallucination-leaderboard)\]
      • [paper - deepmind/long-form-factuality)\]
      • [paper - science/RefChecker)\]\[[HaluAgent](https://github.com/RUCAIBox/HaluAgent)\]\[[LLMsKnow](https://github.com/technion-cs-nlp/LLMsKnow)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [blog - llm-inference-backends)\]\[[CSE 234: Data Systems for Machine Learning](https://hao-ai-lab.github.io/cse234-w25/index.html)\]\[[CS 598: Systems for Generative AI](https://github.com/fanlai0990/CS598)\]
      • [blog
      • [paper
      • [blog - project/sglang)\]\[[sgl-learning-materials](https://github.com/sgl-project/sgl-learning-materials)\]\[[Genai-Bench](https://github.com/sgl-project/genai-bench)\]\[[SpecForge](https://github.com/sgl-project/SpecForge)\]\[[PD Disaggregation and Large-scale Expert Parallelism](https://lmsys.org/blog/2025-05-05-large-scale-ep/)\]\[[Transformers backend integration in SGLang](https://huggingface.co/blog/transformers-backend-sglang)\]
      • [paper - 2](https://arxiv.org/abs/2406.16858)\]\[[EAGLE-3](https://arxiv.org/abs/2503.01840)\]\[[SpecForge](https://lmsys.org/blog/2025-07-25-spec-forge/)\]\[[LLMSpeculativeSampling](https://github.com/feifeibear/LLMSpeculativeSampling)\]\[[Sequoia](https://github.com/Infini-AI-Lab/Sequoia)\]\[[HASS](https://arxiv.org/abs/2408.15766)\]\[[LongSpec](https://github.com/sail-sg/LongSpec)\]\[[FastMTP](https://github.com/Tencent-BAC/FastMTP)\]
      • [paper - serve)\]\[[SARATHI](https://arxiv.org/abs/2308.16369)\]\[[ORCA OSDI 2022](https://www.usenix.org/system/files/osdi22-yu.pdf)\]\[[continuous batching blog](https://www.anyscale.com/blog/continuous-batching-llm-inference)\]\[[vattention](https://github.com/microsoft/vattention)\]
      • [paper
      • [paper - sys/prompt-cache)\]\[[FastServe](https://arxiv.org/abs/2305.05920)\]\[[LMCache](https://github.com/LMCache/LMCache)\]
      • [paper
      • [paper - offloading)\]
      • [paper - ai/ESFT)\]\[[Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts](https://arxiv.org/abs/2408.15664)\]\[[On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models](https://arxiv.org/abs/2501.11873)\]
      • [paper - into-MoEs)\]
      • [paper - Survey-on-Mixture-of-Experts)\]
      • [paper - of-Experts](https://github.com/ZihanWang314/coe)\]
      • [paper - GA)\]\[[LoRA-Pro blog](https://kexue.fm/archives/10266)\]\[[dora](https://github.com/catid/dora)\]\[[PiSSA](https://github.com/GraphPKU/PiSSA)\]
      • [paper - hub/adapters)\]\[[A Survey on LoRA of Large Language Models](https://arxiv.org/abs/2407.11046)\]
      • [paper - Pro)\]
      • [paper
      • [paper
      • [paper
      • [paper
      • [paper
      • [paper - prompting)\]\[[docs](http://platform.openai.com/docs/guides/prompt-generation?context=structured-output-schema)\]
      • [paper - team/appl)\]\[[sammo](https://github.com/microsoft/sammo)\]\[[prompt-poet](https://github.com/character-ai/prompt-poet)\]\[[ell](https://github.com/MadcowD/ell)\]
      • [paper
      • [paper
      • [paper - Survey)\]
      • [paper - Augmented Generation for Natural Language Processing: A Survey](https://arxiv.org/abs/2407.13193)\]\[[A Survey on RAG Meeting LLMs](https://arxiv.org/abs/2405.06211)\]\[[A Comprehensive Survey of Retrieval-Augmented Generation](https://arxiv.org/abs/2410.12837)\]
      • [paper
      • [paper
      • [paper - isf)\]
      • [paper - RAG)\]\[[Adaptive-RAG](https://github.com/starsuzi/Adaptive-RAG)\]\[[Advanced RAG 11: Query Classification and Refinement](https://ai.gopubby.com/advanced-rag-11-query-classification-and-refinement-2aec79f4140b)\]
      • [paper - ecosystem-engineering/Blended-RAG)\]\[[infinity](https://github.com/infiniflow/infinity)\]
      • [paper - NLPIR/FlashRAG)\]\[[FlashRAG-Paddle](https://github.com/RUC-NLPIR/FlashRAG-Paddle)\]\[[Auto-RAG](https://github.com/ictnlp/Auto-RAG)\]\[[flexrag](https://github.com/ictnlp/flexrag)\]\[[LevelRAG](https://github.com/ictnlp/LevelRAG)\]
      • [paper
      • [paper - FiT)\]\[[fastRAG](https://github.com/IntelLabs/fastRAG)\]\[[rag-retrieval-study](https://github.com/intellabs/rag-retrieval-study)\]
      • [paper - new)\]\[[ind_kdd_2024/](https://www.biendata.net/competition/ind_kdd_2024/)\]\[[KDD2024-WhoIsWho-Top3](https://github.com/yanqiangmiffy/KDD2024-WhoIsWho-Top3)\]
      • [paper - io/memobase)\]\[[A-MEM](https://arxiv.org/abs/2502.12110)\]\[[cognee](https://github.com/topoteretes/cognee)\]
      • [blog - Augmented Generation for Large Language Models](https://arxiv.org/abs/2409.13385)\]\[[ContextRAG](https://arxiv.org/abs/2502.14759)\]\[[LongRefiner](https://github.com/ignorejjj/LongRefiner)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]
      • [RAG-Retrieval - Shanghai/PGRAG)\]\[[CRUD_RAG](https://github.com/IAAR-Shanghai/CRUD_RAG)\]\[[PlanRAG](https://github.com/myeon9h/PlanRAG)\]\[[DPA-RAG](https://github.com/dongguanting/DPA-RAG)\]\[[FollowRAG](https://github.com/dongguanting/FollowRAG)\]\[[LongRAG](https://github.com/TIGER-AI-Lab/LongRAG)\]\[[structured-rag](https://github.com/weaviate/structured-rag)\]\[[RAGLab](https://github.com/fate-ubw/RAGLab)\]\[[autogluon-rag](https://github.com/autogluon/autogluon-rag)\]\[[VARAG](https://github.com/adithya-s-k/VARAG)\]\[[PAI-RAG](https://github.com/aigc-apps/PAI-RAG)\]\[[RagVL](https://github.com/IDEA-FinAI/RagVL)\]\[[AutoRAG](https://github.com/Marker-Inc-Korea/AutoRAG)\]\[[RetroLLM](https://github.com/sunnynexus/RetroLLM)\]\[[RAG-Instruct](https://github.com/FreedomIntelligence/RAG-Instruct)\]\[[RapidRAG](https://github.com/RapidAI/RapidRAG)\]\[[UltraRAG](https://github.com/OpenBMB/UltraRAG)\]
      • [paper - benchmark/mteb)\]\[[leaderboard](https://huggingface.co/spaces/mteb/leaderboard)\]\[[MMTEB](https://arxiv.org/abs/2502.13595)\]\[[MIEB](https://arxiv.org/abs/2504.10471)\]
      • [paper
      • [paper
      • [paper - long.194/)\]\[[llm_reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/research/llm_reranker)\]\[[FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding)\]
      • [paper - basis-bge-zh/)\]
      • [paper - large-zh)\]\[[gte-Qwen2-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct)\]\[[gte-large-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5)\]\[[gme-Qwen2-VL-2B-Instruct](https://huggingface.co/Alibaba-NLP/gme-Qwen2-VL-2B-Instruct)\]
      • [CohereV3
      • [paper - ai/instructor-embedding)\]
      • [paper - mistral-7b-instruct)\]\[[llm2vec](https://github.com/McGill-NLP/llm2vec)\]\[[When Text Embedding Meets Large Language Model: A Comprehensive Survey](https://arxiv.org/abs/2412.09165)\]\[[LongEmbed](https://github.com/dwzhu-pku/LongEmbed)\]
      • [paper - ai/contrastors)\]\[[nomic-embed-vision-v1.5](https://huggingface.co/nomic-ai/nomic-embed-vision-v1.5)\]\[[nomic-embed-text-v2-moe](https://huggingface.co/nomic-ai/nomic-embed-text-v2-moe)\]
      • [paper
      • [paper - NLP/llm2vec)\]\[[VLM2Vec](https://github.com/TIGER-AI-Lab/VLM2Vec)\]\[[Gemini Embedding](https://arxiv.org/abs/2503.07891)\]
      • [paper - Embed-v1)\]\[[nv-ingest](https://github.com/NVIDIA/nv-ingest)\]\[[EmbeddingGemma](https://arxiv.org/abs/2509.20354)\]
      • [paper
      • [JamAIBase - Retrieval](https://github.com/NovaSearch-Team/RAG-Retrieval)\]\[[Tevatron](https://github.com/texttron/tevatron)\]\[[model2vec](https://github.com/MinishLab/model2vec)\]
      • [paper - Of-Thoughts)\]
      • [paper - of-Thoughts-XoT)\]
      • [paper - of-thoughts)\]
      • [paper - husky/Husky-v1)\]\[[QueryAgent](https://github.com/cdhx/QueryAgent)\]\[[OctoTools](https://github.com/octotools/octotools)\]\[[START](https://arxiv.org/abs/2503.04625)\]\[[ZeroTIR](https://arxiv.org/abs/2505.07773)\]
      • [paper - System)\]
      • [paper
      • [paper - st)\]
      • [paper - MCTS)\]\[[llm-mcts](https://github.com/1989Ryan/llm-mcts)\]\[[LightZero](https://github.com/opendilab/LightZero)\]\[[Agent-R](https://github.com/bytedance/Agent-R)\]\[[atom](https://github.com/qixucen/atom)\]
      • [paper - Math](https://arxiv.org/abs/2501.04519)\]\[[Orca 2](https://arxiv.org/abs/2311.11045)\]\[[STaR](https://arxiv.org/abs/2203.14465)\]\[[Quiet-STaR](https://arxiv.org/abs/2403.09629)\]
      • [blog - of-thought-monitoring)\]\[[Agent Q](https://arxiv.org/abs/2408.07199)\]\[[Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://arxiv.org/abs/2408.03314)\]\[[search-and-learn](https://github.com/huggingface/search-and-learn)\]\[[Let's Verify Step by Step](https://arxiv.org/abs/2305.20050)\]\[[Thinking LLMs: General Instruction Following with Thought Generation](https://arxiv.org/abs/2410.10630)\]\[[Awesome-LLM-Strawberry](https://github.com/hijkzzz/Awesome-LLM-Strawberry)\]\[[Awesome-LLM-Reasoning](https://github.com/atfortes/Awesome-LLM-Reasoning)\]\[[Claude's extended thinking](https://www.anthropic.com/research/visible-extended-thinking)\]\[[claude-think-tool](https://www.anthropic.com/engineering/claude-think-tool)\]
      • [paper
      • [paper
      • [paper - 2-research](https://github.com/open-thought/system-2-research)\]\[[Test-time Computing: from System-1 Thinking to System-2 Thinking](https://arxiv.org/abs/2501.02497)\]\[[Towards System 2 Reasoning in LLMs](https://arxiv.org/abs/2501.04682)\]\[[Awesome-System2-Reasoning-LLM](https://github.com/zzli2022/Awesome-System2-Reasoning-LLM)\]
      • [paper
      • [paper - Efficient Model Ladders](https://arxiv.org/abs/2412.04403)\]\[[Inference Scaling Laws](https://arxiv.org/abs/2408.00724)\]\[[Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models](https://arxiv.org/abs/2501.12370)\]\[[Distillation Scaling Laws](https://arxiv.org/abs/2502.08606)\]
      • [paper
      • [paper - zhu.com/part-2-grade-school-math/part-2-1)\]
      • [paper
      • [blog - interpretability)\]\[[transformer-debugger](https://github.com/openai/transformer-debugger)\]
      • [blog
      • [blog - thoughts-language-model)\]\[[Open-sourcing circuit tracing tools](https://www.anthropic.com/research/open-source-circuit-tracing)\]\[[circuit-tracer](https://github.com/safety-research/circuit-tracer)\]\[[Persona Vectors](https://arxiv.org/abs/2507.21509)\]
      • [paper - Explainability](https://github.com/hila-chefer/Transformer-Explainability)\]
      • [paper - transparency-tool)\]\[[LLM-Microscope](https://arxiv.org/abs/2502.15007)\]
      • [paper - explainer)\]\[[demo](https://poloclub.github.io/transformer-explainer)\]
      • [paper
      • [paper - 130B)\]
      • [paper
      • [paper - AI/Telechat)\]\[[TeleChat2](https://github.com/Tele-AI/TeleChat2)\]\[[Tele-FLM Technical Report](https://arxiv.org/abs/2404.16645)\]\[[Tele-FLM](https://huggingface.co/CofeAI/Tele-FLM)\]\[[Tele-FLM-1T](https://huggingface.co/CofeAI/Tele-FLM-1T)\]\[[Technical Report of TeleChat2, TeleChat2.5 and T1](https://arxiv.org/abs/2507.18013)\]
      • [paper - LLaMA-Alpaca)\]\[[Chinese-LLaMA-Alpaca-2](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2)\]\[[Chinese-LLaMA-Alpaca-3](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3)\]\[[baby-llama2-chinese](https://github.com/DLLXW/baby-llama2-chinese)\]
      • [paper
      • [paper - GSAI/Llama-3-SynE)\]
      • [paper - CoT)\]
      • [paper - gpt4s-mistakes-with-gpt-4)\]\[[Heimdall](https://arxiv.org/abs/2504.10337)\]\[[Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning](https://arxiv.org/abs/2410.08146)\]\[[Agentic Reward Modeling](https://arxiv.org/abs/2502.19328)\]\[[Reward Hacking in Reinforcement Learning](https://lilianweng.github.io/posts/2024-11-28-reward-hacking)\]\[[DeepSeek-GRM](https://arxiv.org/abs/2504.02495)\]\[[RM-R1](https://github.com/RM-R1-UIUC/RM-R1)\]\[[RewardAnything](https://arxiv.org/abs/2506.03637)\]\[[Skywork-Reward-V2](https://arxiv.org/abs/2507.01352)\]\[[POLAR](https://github.com/InternLM/POLAR)\]
      • [paper
      • [paper - NLP/VinePPO)\]\[[OpenRFT](https://github.com/ADaM-BJTU/OpenRFT)\]\[[SoRFT](https://arxiv.org/abs/2502.20127)\]\[[MRT](https://cohenqu.github.io/mrt.github.io/)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[AdaRFT](https://github.com/uscnlp-lime/verl)\]\[[Trinity-RFT](https://github.com/modelscope/Trinity-RFT)\]
      • [paper - AI4Code/HyperAgent)\]\[[Seeker](https://github.com/XMZhangAI/Seeker)\]\[[AutoKaggle](https://github.com/multimodal-art-projection/AutoKaggle)\]\[[Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level](https://arxiv.org/abs/2411.03562)\]\[[ML-Agent](https://github.com/MASWorks/ML-Agent)\]\[[MLE-Dojo](https://github.com/MLE-Dojo/MLE-Dojo)\]\[[DeepAnalyze](https://github.com/ruc-datalab/DeepAnalyze)\]
      • [blog
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]
      • [paper
      • [blog - llama/llama-32-66f448ffc8c32f949b04c8cf)\]\[[llama-stack](https://github.com/meta-llama/llama-stack)\]\[[llama-stack-apps](https://github.com/meta-llama/llama-stack-apps)\]\[[lingua](https://github.com/facebookresearch/lingua)\]\[[llama-assistant](https://github.com/vietanhdev/llama-assistant)\]\[[minimind-v](https://github.com/jingyaogong/minimind-v)\]\[[nanoVLM](https://github.com/huggingface/nanoVLM)\]\[[Llama3.2-Vision-Finetune](https://github.com/2U1/Llama3.2-Vision-Finetune)\]
      • [paper - PaLM)\]
      • [Awesome-LegalAI-Resources - compass/LawBench)\]
      • [paper
      • [paper - NLP/ProX)\]
      • [paper - Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)\]\[[DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)\]\[[OmniDocBench](https://github.com/opendatalab/OmniDocBench)\]\[[Document Parsing Unveiled](https://arxiv.org/abs/2410.21169)\]\[[Docling Technical Report](https://arxiv.org/abs/2408.09869)\]\[[markitdown](https://github.com/microsoft/markitdown)\]\[[pandoc](https://github.com/jgm/pandoc)\]\[[Dolphin](https://github.com/bytedance/Dolphin)\]\[[LangExtract](https://github.com/google/langextract)\]\[[Logics-Parsing](https://github.com/alibaba/Logics-Parsing)\]
      • [paper
      • [paper - cross-capabilities)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper - Honesty-Survey)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]
      • [paper - NLP/VinePPO)\]
      • [paper - sia.github.io)\]\[[VC-PPO](https://arxiv.org/abs/2503.01491)\]\[[Pre-PPO](https://arxiv.org/abs/2503.22230)\]\[[VAPO](https://arxiv.org/abs/2504.05118)\]\[[EMPO](https://arxiv.org/abs/2504.05812)\]\[[POLARIS](https://honorable-payment-890.notion.site/POLARIS-A-POst-training-recipe-for-scaling-reinforcement-Learning-on-Advanced-ReasonIng-modelS-1dfa954ff7c38094923ec7772bf447a1)\]\[[TreePO](https://arxiv.org/abs/2508.17445)\]
      • [evaluation-guidebook - LLM-Eval](https://github.com/onejune2018/Awesome-LLM-Eval)\]\[[LLM-eval-survey](https://github.com/MLGroupJLU/LLM-eval-survey)\]\[[llm_benchmarks](https://github.com/leobeeson/llm_benchmarks)\]\[[Awesome-LLMs-Evaluation-Papers](https://github.com/tjunlp-lab/Awesome-LLMs-Evaluation-Papers)\]
      • [paper
      • [paper - Robotics/EO-1)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]
      • [swarm - AI/AgentStack)\]\[[multi-agent-orchestrator](https://github.com/awslabs/multi-agent-orchestrator)\]\[[smolagents](https://github.com/huggingface/smolagents)\]\[[agent-service-toolkit](https://github.com/JoshuaC215/agent-service-toolkit)\]\[[agno](https://github.com/agno-agi/agno)\]\[[ANUS](https://github.com/nikmcfly/ANUS)\]\[[AutoAgent](https://github.com/HKUDS/AutoAgent)\]\[[AgentIQ](https://github.com/NVIDIA/AgentIQ)\]
      • [paper - baichuan-mllm/bc-omni)\]\[[Baichuan-Omni-1.5 Technical Report](https://arxiv.org/abs/2501.15368)\]\[[Baichuan-Omni-1.5](https://github.com/baichuan-inc/Baichuan-Omni-1.5)\]
      • [paper - research/SpatialLM)\]\[[3D-R1](https://github.com/AIGeeksGroup/3D-R1)\]\[[RynnEC](https://github.com/alibaba-damo-academy/RynnEC)\]
      • [paper - PaLM)\]
      • [paper - bench)\]\[[swarm](https://github.com/openai/swarm)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [paper - Anything](https://github.com/HKUDS/RAG-Anything)\]\[[KAG](https://github.com/OpenSPG/KAG)\]\[[HybGRAG](https://arxiv.org/abs/2412.16311)\]\[[CAG](https://github.com/hhhuang/CAG)\]\[[GraphRAG](https://github.com/JayLZhou/GraphRAG)\]\[[Graph-R1](https://github.com/LHRLAB/Graph-R1)\]\[[Youtu-GraphRAG](https://arxiv.org/abs/2508.19855)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]
      • [paper - han-lab/duo-attention)\]\[[Star-Attention](https://github.com/NVIDIA/Star-Attention)\]\[[LoongServe](https://arxiv.org/abs/2404.09526)\]\[[FlexPrefill](https://github.com/ByteDance-Seed/FlexPrefill)\]
      • [paper
      • [paper - ml/RoboticsDiffusionTransformer)\]\[[Video Prediction Policy](https://github.com/roboterax/video-prediction-policy)\]\[[Humanoid-Gym](https://github.com/roboterax/humanoid-gym)\]\[[RoboMaster](https://github.com/KwaiVGI/RoboMaster)\]\[[OpenWBT](https://github.com/GalaxyGeneralRobotics/OpenWBT)\]\[[BridgeVLA](https://github.com/BridgeVLA/BridgeVLA)\]\[[3D Diffusion Policy](https://github.com/YanjieZe/3D-Diffusion-Policy)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]
      • [paper - deepmind/synthid-text)\]
      • [paper - Actor](https://github.com/microsoft/GUI-Actor)\]\[[Phi-Ground Tech Report](https://arxiv.org/abs/2507.23779)\]\[[Agent-S](https://github.com/simular-ai/Agent-S)\]\[[The Dawn of GUI Agent](https://arxiv.org/abs/2411.10323)\]\[[ShowUI](https://github.com/showlab/ShowUI)\]\[[Aria-UI](https://github.com/AriaUI/Aria-UI)\]\[[aguvis](https://github.com/xlang-ai/aguvis)\]\[[TinyClick](https://github.com/SamsungLabs/TinyClick)\]\[[InfiGUIAgent](https://github.com/Reallm-Labs/InfiGUIAgent)\]\[[autoMate](https://github.com/yuruotong1/autoMate)\]
      • [paper - PaLM)\]
      • [paper
      • [paper - embedding-torch](https://github.com/lucidrains/rotary-embedding-torch)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]
      • [paper - project/selfcodealign)\]
      • [paper - deepmind/synthid-text)\]
      • [paper - NLP-SG/CoI-Agent)\]\[[AI-Researcher](https://github.com/HKUDS/AI-Researcher)\]\[[Researcher](https://github.com/zhu-minjun/Researcher)\]
      • [paper - Modal Search](https://arxiv.org/abs/2408.14698)\]\[[M3DocRAG](https://arxiv.org/abs/2411.04952)\]\[[Visualized BGE](https://github.com/FlagOpen/FlagEmbedding/tree/master/research/visual_bge)\]\[[OmniSearch](https://github.com/Alibaba-NLP/OmniSearch)\]\[[StreamRAG](https://github.com/video-db/StreamRAG)\]\[[VisRAG](https://github.com/OpenBMB/VisRAG)\]\[[LamRA](https://github.com/Code-kunkun/LamRA)\]
      • [paper - PaLM)\]
      • [paper - nlp/ProLong)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]
      • [paper - NLP/O1-Journey)\]\[[O1 Replication Journey -- Part 2](https://arxiv.org/abs/2411.16489)\]\[[O1 Replication Journey -- Part 3](https://arxiv.org/abs/2501.06458)\]\[[Scaling of Search and Learning](https://arxiv.org/abs/2412.14135)\]\[[Revisiting the Test-Time Scaling of o1-like Models](https://arxiv.org/abs/2502.12215)\]\[[LLaMA-O1](https://github.com/SimpleBerry/LLaMA-O1)\]\[[Marco-o1](https://github.com/AIDC-AI/Marco-o1)\]\[[QwQ-32B](https://qwenlm.github.io/blog/qwq-32b)\]\[[qvq-72b-preview](https://qwenlm.github.io/blog/qvq-72b-preview)\]\[[QwQ-Max-Preview](https://qwenlm.github.io/blog/qwq-max-preview)\]\[[SkyThought](https://github.com/NovaSky-AI/SkyThought)\]\[[On the Overthinking of o1-Like LLMs](https://arxiv.org/abs/2412.21187)\]\[[On the Underthinking of o1-Like LLMs](https://arxiv.org/abs/2501.18585)\]\[[Reinforcing Cognitive Experts](https://arxiv.org/abs/2505.14681)\]
      • [paper - Hunyuan-Large)\]\[[Hunyuan-A13B](https://github.com/Tencent-Hunyuan/Hunyuan-A13B)\]\[[Hunyuan-TurboS](https://arxiv.org/abs/2505.15431)\]\[[TransMamba](https://arxiv.org/abs/2503.24067)\]\[[FastCuRL](https://arxiv.org/abs/2503.17287)\]
      • [paper - Lab](https://github.com/THUDM/Android-Lab)\]
      • [paper - deepmind/synthid-text)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]
      • [paper - fib-lab/ACL24-EconAgent)\]\[[Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://arxiv.org/abs/2312.11970)\]
      • [paper - Shanghai/SurveyX)\]\[[SurveyForge](https://github.com/Alpha-Innovator/SurveyForge)\]
      • [paper - CoT)\]\[[alphageometry](https://github.com/google-deepmind/alphageometry)\]\[[AlphaGeometry2](https://arxiv.org/abs/2502.03544)\]\[[AlphaEvolve](https://deepmind.google/discover/blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/)\]\[[OpenEvolve](https://github.com/codelion/openevolve)\]\[[Gemini with Deep Think](https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/)\]\[[MathCritique](https://github.com/WooooDyy/MathCritique)\]\[[PromptCoT](https://github.com/inclusionAI/PromptCoT)\]\[[ShinkaEvolve](https://github.com/SakanaAI/ShinkaEvolve)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]
      • [alphafold3 - deepmind/alphafold)\]\[[RoseTTAFold](https://github.com/RosettaCommons/RoseTTAFold)\]\[[RFdiffusion](https://github.com/RosettaCommons/RFdiffusion)\]\[[AlphaGenome](https://github.com/google-deepmind/alphagenome)\]
      • [paper - llm/OpenCoder-llm)\]\[[dataset](https://huggingface.co/collections/OpenCoder-LLM/opencoder-datasets-672e6db6a0fed24bd69ef1c2)\]\[[opc_data_filtering](https://github.com/OpenCoder-llm/opc_data_filtering)\]\[[OpenCodeEval](https://github.com/richardodliu/OpenCodeEval)\]
      • [paper - deepmind/synthid-text)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper - cs-nlp/LLMsKnow)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]
      • [paper - Embed/blob/main/modeling_nvmmembed.py)\]\[[magiclens](https://github.com/google-deepmind/magiclens)\]\[[E5-V](https://github.com/kongds/E5-V)\]\[[Visualized BGE](https://github.com/FlagOpen/FlagEmbedding/tree/master/research/visual_bge)\]\[[VLM2Vec](https://github.com/TIGER-AI-Lab/VLM2Vec)\]\[[GME-Qwen2-VL](https://arxiv.org/abs/2412.16855)\]\[[mmE5](https://github.com/haon-chen/mmE5)\]\[[LLaVE](https://github.com/DeepLearnXMU/LLaVE)\]\[[perception_models](https://github.com/facebookresearch/perception_models)\]\[[UniME](https://github.com/deepglint/UniME)\]\[[MetaEmbed](https://arxiv.org/abs/2509.18095)\]\[[SAIL-Embedding](https://arxiv.org/abs/2510.12709)\]
      • [paper - YuanGroup/LLaVA-CoT)\]\[[internvl2.0_mpo](https://github.com/OpenGVLab/InternVL/tree/main/internvl_chat/shell/internvl2.0_mpo)\]\[[Insight-V](https://github.com/dongyh20/Insight-V)\]\[[VisVM](https://arxiv.org/abs/2412.03704)\]\[[Mulberry](https://github.com/HJYao00/Mulberry)\]\[[AR-MCTS](https://arxiv.org/abs/2412.14835)\]\[[Virgo](https://arxiv.org/abs/2501.01904)\]\[[Virgo](https://github.com/RUCAIBox/Virgo)\]\[[LlamaV-o1](https://arxiv.org/abs/2501.06186)\]\[[Sherlock](https://github.com/DripNowhy/Sherlock)\]\[[Image-Generation-CoT](https://github.com/ZiyuGuo99/Image-Generation-CoT)\]\[[Awesome-MLLM-Reasoning](https://github.com/WillDreamer/Awesome-MLLM-Reasoning)\]\[[Multimodal Chain-of-Thought Reasoning](https://arxiv.org/abs/2503.12605)\]\[[A Survey on Large Multimodal Reasoning Models](https://arxiv.org/abs/2505.04921)\]\[[Awesome-RL-based-Reasoning-MLLMs](https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs)\]
      • [paper - SQL)\]\[[vanna](https://github.com/vanna-ai/vanna)\]\[[NL2SQL_Handbook](https://github.com/HKUSTDial/NL2SQL_Handbook)\]\[[Spider2](https://github.com/xlang-ai/Spider2)\]\[[WrenAI](https://github.com/Canner/WrenAI)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]
      • [paper - Aware Training](https://arxiv.org/abs/2505.14302)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - AutoML/MobileVLM)\]\[[MobileVLM V2](https://arxiv.org/abs/2402.03766)\]\[[BlueLM-V-3B](https://arxiv.org/abs/2411.10640)\]\[[XiaoMi/mobilevlm](https://github.com/XiaoMi/mobilevlm)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]
      • [paper - deep-researcher](https://github.com/langchain-ai/ollama-deep-researcher)\]\[[PaSa](https://arxiv.org/abs/2501.10120)\]\[[ScholarCopilot](https://github.com/TIGER-AI-Lab/ScholarCopilot)\]\[[Ai2 ScholarQA](https://github.com/allenai/ai2-scholarqa-lib)\]\[[ScholarSearch](https://arxiv.org/abs/2506.13784)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - VL](https://github.com/FlagOpen/FlagEmbedding/tree/master/research/BGE_VL)\]\[[MegaPairs](https://github.com/VectorSpaceLab/MegaPairs)\]\[[BGE-VL-base](https://huggingface.co/BAAI/BGE-VL-base)\]\[[BGE-VL-Screenshot](https://github.com/FlagOpen/FlagEmbedding/tree/master/research/BGE_VL_Screenshot)\]\[[BGE-Coder](https://github.com/FlagOpen/FlagEmbedding/tree/master/research/BGE_Coder)\]
      • [paper - instruct)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper - ai/xgrammar)\]\[[mlc-llm](https://github.com/mlc-ai/mlc-llm)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - 3's Context Ten-Fold Overnight](https://github.com/FlagOpen/FlagEmbedding/tree/master/research/Long_LLM/longllm_qlora)\]\[[From 128K to 4M](https://arxiv.org/abs/2504.06214)\]
      • [paper - infra/sandbox)\]\[[trae-agent](https://github.com/bytedance/trae-agent)\]\[[BitsAI-CR](https://arxiv.org/abs/2501.15134)\]
      • [paper - BJTU/O1-CODER)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]
      • [paper - PaLM)\]
      • [paper - SJTU/MING)\]\[[EmoLLM](https://github.com/SmartFlowAI/EmoLLM)\]
      • [paper - Web/AIPress-code)\]
      • [paper
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - tech/colpali)\]\[[VARAG](https://github.com/adithya-s-k/VARAG)\]\[[ColiVara](https://github.com/tjmlabs/ColiVara)\]\[[docling](https://github.com/docling-project/docling)\]\[[M3DocRAG](https://arxiv.org/abs/2411.04952)\]\[[Visualized BGE](https://github.com/FlagOpen/FlagEmbedding/tree/master/research/visual_bge)\]\[[OmniSearch](https://github.com/Alibaba-NLP/OmniSearch)\]\[[nv-ingest](https://github.com/NVIDIA/nv-ingest)\]
      • [paper - 1M Technical Report](https://arxiv.org/abs/2501.15383)\]\[[QwenLong-CPRS](https://arxiv.org/abs/2505.18092)\]\[[QwQ](https://github.com/QwenLM/QwQ)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper - PaLM)\]
      • [paper
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [blog - recurrent-drafter)\]\[[A Hitchhiker's Guide to Speculative Decoding](https://pytorch.org/blog/hitchhikers-guide-speculative-decoding)\]
      • [paper
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - guided Tree Search](https://arxiv.org/abs/2411.11694)\]\[[An Empirical Study on Eliciting and Improving R1-like Reasoning Models](https://arxiv.org/abs/2503.04548)\]\[[Towards Large Reasoning Models](https://arxiv.org/abs/2501.09686)\]\[[Reasoning models don't always say what they think](https://www.anthropic.com/research/reasoning-models-dont-say-think)\]\[[Detecting misbehavior in frontier reasoning models](https://openai.com/index/chain-of-thought-monitoring/)\]\[[Monitoring Reasoning Models](https://arxiv.org/abs/2503.11926)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]\[[The State of LLM Reasoning Models](https://sebastianraschka.com/blog/2025/state-of-llm-reasoning-and-inference-scaling.html)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - Copilot/OS-Genesis)\]\[[homepage](https://qiushisun.github.io/OS-Genesis-Home/)\]
      • [paper - ai/DeepSeek-V3)\]\[[DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1)\]\[[DeepEP](https://github.com/deepseek-ai/DeepEP)\]\[[open-infra-index](https://github.com/deepseek-ai/open-infra-index)\]\[[Insights into DeepSeek-V3](https://arxiv.org/abs/2505.09343)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - o1)\]\[[MedVLM-R1](https://arxiv.org/abs/2502.19634)\]\[[m1](https://github.com/UCSC-VLAA/m1)\]\[[MedReason](https://github.com/UCSC-VLAA/MedReason)\]\[[X-Reasoner](https://arxiv.org/abs/2505.03981)\]\[[AlphaMed](https://arxiv.org/abs/2505.17952)\]\[[Lingshu](https://arxiv.org/abs/2506.07044)\]\[[ReasonMed](https://arxiv.org/abs/2506.09513)\]\[[MedResearcher-R1](https://github.com/AQ-MedAI/MedResearcher-R1)\]\[[ReasonMed](https://github.com/alibaba-damo-academy/ReasonMed)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - NLP/PC-Agent)\]\[[PC-Agent-E](https://github.com/GAIR-NLP/PC-Agent-E)\]\[[PPTAgent](https://github.com/icip-cas/PPTAgent)\]\[[PosterAgent](https://github.com/Paper2Poster/Paper2Poster)\]\[[MultiAgentPPT](https://github.com/johnson7788/MultiAgentPPT)\]\[[PresentAgent](https://github.com/AIGeeksGroup/PresentAgent)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper - Curieous/Curie)\]\[[Paper2Code](https://github.com/going-doer/Paper2Code)\]\[[Paper2Poster](https://github.com/Paper2Poster/Paper2Poster)\]\[[PosterGen](https://github.com/Y-Research-SBU/PosterGen)\]\[[Paper2Agent](https://github.com/jmiao24/Paper2Agent)\]\[[Paper2Video](https://github.com/showlab/Paper2Video)\]\[[Auto-Slides](https://github.com/Westlake-AGI-Lab/Auto-Slides)\]
      • [paper
      • [paper - Coder](https://arxiv.org/abs/2505.21297)\]\[[rStar2-Agent](https://arxiv.org/abs/2508.20722)\]\[[PRIME](https://github.com/PRIME-RL/PRIME)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - AI/MiniMax-01)\]\[[MiniMax-M1](https://github.com/MiniMax-AI/MiniMax-M1)\]\[[MiniMax-M2](https://github.com/MiniMax-AI/MiniMax-M2)\]\[[Step-3](https://arxiv.org/abs/2507.19427)\]\[[Linear-MoE](https://github.com/OpenSparseLLMs/Linear-MoE)\]\[[dots.llm1 Technical Report](https://arxiv.org/abs/2506.05767)\]\[[RedOne](https://arxiv.org/abs/2507.10605)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper
      • [paper - PaLM)\]
      • [paper - quality-chinese-training-datasets-66cfed105f502ece8f29643e)\]\[[MIG](https://arxiv.org/abs/2504.13835)\]\[[A Survey of LLM × DATA](https://arxiv.org/abs/2505.18458)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - CoT](https://github.com/InternLM/SIM-CoT)\]
      • [paper - augmented-visual-question-answering)\]\[[ViDoRAG](https://github.com/Alibaba-NLP/ViDoRAG)\]\[[Gurubase](https://github.com/Gurubase/gurubase)\]\[[LamRA](https://github.com/Code-kunkun/LamRA)\]\[[RAG-Anything](https://github.com/HKUDS/RAG-Anything)\]
      • [paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - TARS)\]\[[UI-TARS-desktop](https://github.com/bytedance/UI-TARS-desktop)\]\[[UI-TARS-2](https://arxiv.org/abs/2509.02544)\]\[[Game-TARS](https://arxiv.org/abs/2510.23691)\]\[[midscene](https://github.com/web-infra-dev/midscene)\]\[[browser-use](https://github.com/browser-use/browser-use)\]\[[BrowserOS](https://github.com/browseros-ai/BrowserOS)\]\[[computer_use_ootb](https://github.com/showlab/computer_use_ootb)\]\[[Agent-S](https://github.com/simular-ai/Agent-S)\]\[[open-operator](https://github.com/All-Hands-AI/open-operator)\]\[[STEVE-R1](https://github.com/FanbinLu/STEVE-R1)\]\[[UI-R1](https://arxiv.org/abs/2503.21620)\]\[[InfiGUI-R1](https://github.com/Reallm-Labs/InfiGUI-R1)\]\[[r1-computer-use](https://github.com/agentsea/r1-computer-use)\]\[[cua](https://github.com/trycua/cua)\]\[[GUI-G1](https://github.com/Yuqi-Zhou/GUI-G1)\]\[[ZeroGUI](https://github.com/OpenGVLab/ZeroGUI)\]\[[OpenCUA](https://github.com/xlang-ai/OpenCUA)\]\[[UI-Venus](https://arxiv.org/abs/2508.10833)\]\[[ScaleCUA](https://github.com/OpenGVLab/ScaleCUA)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper - ai/flashinfer)\]\[[Mirage Persistent Kernel](https://github.com/mirage-project/mirage)\]
      • [paper
      • [paper - Chunking](https://github.com/IAAR-Shanghai/Meta-Chunking)\]\[[chonkie](https://github.com/chonkie-inc/chonkie)\]\[[chonky](https://github.com/mirth/chonky)\]\[[PageIndex](https://github.com/VectifyAI/PageIndex)\]\[[Vision-Guided Chunking](https://arxiv.org/abs/2506.16035)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - evolution-pytorch](https://github.com/lucidrains/mind-evolution-pytorch)\]\[[AlphaEvolve](https://deepmind.google/discover/blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/)\]\[[OpenEvolve](https://github.com/codelion/openevolve)\]\[[Results of AlphaEvolve](https://github.com/google-deepmind/alphaevolve_results)\]
      • [paper - k1.5)\]\[[Kimi-K2](https://github.com/MoonshotAI/Kimi-K2)\]\[[Kimi-Researcher](https://moonshotai.github.io/Kimi-Researcher/)\]\[[G1](https://arxiv.org/abs/2505.13426)\]\[[demystify-long-cot](https://github.com/eddycmu/demystify-long-cot)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - Time Compute Optimally can be More Effective than Scaling Model Parameters](https://arxiv.org/abs/2408.03314)\]\[[probabilistic-inference-scaling](https://github.com/probabilistic-inference-scaling/probabilistic-inference-scaling)\]\[[LIMO](https://arxiv.org/abs/2502.03387)\]\[[OpenThinker-32B](https://www.open-thoughts.ai/blog/scale)\]\[[L1](https://github.com/cmu-l3/l1)\]\[[Z1](https://github.com/efficientscaling/Z1)\]\[[Reasoning Models Can Be Effective Without Thinking](https://arxiv.org/abs/2504.09858)\]\[[Thinkless](https://github.com/VainF/Thinkless)\]\[[AdaptThink](https://github.com/THU-KEG/AdaptThink)\]\[[AdaCoT](https://arxiv.org/abs/2505.11896)\]\[[ASRR](https://arxiv.org/abs/2505.15400)\]\[[ThinkDial](https://arxiv.org/abs/2508.18773)\]
      • [paper - db/StreamRAG)\]\[[VideoRAG](https://arxiv.org/abs/2501.05874)\]\[[Ask in Any Modality](https://arxiv.org/abs/2502.08826)\]
      • [OpenDeepResearcher - DeepResearch](https://github.com/jina-ai/node-DeepResearch)\]\[[open-deep-research](https://github.com/nickscamara/open-deep-research)\]\[[open-deep-research blog](https://huggingface.co/blog/open-deep-research)\]\[[open_deep_research](https://github.com/huggingface/smolagents/tree/main/examples/open_deep_research)\]\[[deep-research](https://github.com/dzhng/deep-research)\]\[[deep-research](https://github.com/u14app/deep-research)\]\[[Auto-Deep-Research](https://github.com/HKUDS/Auto-Deep-Research)\]\[[deep-searcher](https://github.com/zilliztech/deep-searcher)\]\[[local-deep-research](https://github.com/LearningCircuit/local-deep-research)\]\[[local-deep-researcher](https://github.com/langchain-ai/local-deep-researcher)\]\[[open_deep_research](https://github.com/langchain-ai/open_deep_research)\]\[[Agentic-Reasoning](https://github.com/theworldofagents/Agentic-Reasoning)\]\[[Awesome-Deep-Research](https://github.com/DavidZWZ/Awesome-Deep-Research)\]\[[DeepResearchAgent](https://github.com/SkyworkAI/DeepResearchAgent)\]\[[Universal Deep Research](https://github.com/NVlabs/UniversalDeepResearch)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper
      • [paper
      • [paper - Agent-Quant](https://arxiv.org/abs/2505.15155)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [paper - Parameter-Efficient-Fine-Tuning-for-Foundation-Models)\]
      • [paper - o1)\]\[[WebThinker](https://github.com/RUC-NLPIR/WebThinker)\]\[[HiRA](https://github.com/RUC-NLPIR/HiRA)\]\[[CoRAG](https://arxiv.org/abs/2501.14342)\]\[[DeepRAG](https://arxiv.org/abs/2502.01142)\]\[[StructRAG](https://github.com/icip-cas/StructRAG)\]\[[ReAG](https://github.com/superagent-ai/reag)\]\[[Search-R1](https://github.com/PeterGriffinJin/Search-R1)\]\[[r1-reasoning-rag](https://github.com/deansaco/r1-reasoning-rag)\]\[[R1-Searcher](https://github.com/RUCAIBox/R1-Searcher)\]\[[MCTS-RAG](https://arxiv.org/abs/2503.20757)\]\[[ReaRAG](https://arxiv.org/abs/2503.21729)\]\[[ReasonRAG](https://github.com/wlzhang2020/ReasonRAG)\]\[[Diver](https://github.com/AQ-MedAI/Diver)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [RAG-Retrieval - Shanghai/PGRAG)\]\[[CRUD_RAG](https://github.com/IAAR-Shanghai/CRUD_RAG)\]\[[PlanRAG](https://github.com/myeon9h/PlanRAG)\]\[[DPA-RAG](https://github.com/dongguanting/DPA-RAG)\]\[[FollowRAG](https://github.com/dongguanting/FollowRAG)\]\[[LongRAG](https://github.com/TIGER-AI-Lab/LongRAG)\]\[[structured-rag](https://github.com/weaviate/structured-rag)\]\[[RAGLab](https://github.com/fate-ubw/RAGLab)\]\[[autogluon-rag](https://github.com/autogluon/autogluon-rag)\]\[[VARAG](https://github.com/adithya-s-k/VARAG)\]\[[PAI-RAG](https://github.com/aigc-apps/PAI-RAG)\]\[[RagVL](https://github.com/IDEA-FinAI/RagVL)\]\[[AutoRAG](https://github.com/Marker-Inc-Korea/AutoRAG)\]\[[RetroLLM](https://github.com/sunnynexus/RetroLLM)\]\[[RAG-Instruct](https://github.com/FreedomIntelligence/RAG-Instruct)\]\[[RapidRAG](https://github.com/RapidAI/RapidRAG)\]\[[UltraRAG](https://github.com/OpenBMB/UltraRAG)\]\[[MMOA-RAG](https://github.com/chenyiqun/MMOA-RAG)\]\[[EasyRAG](https://github.com/BUAADreamer/EasyRAG)\]\[[HiRAG](https://github.com/hhy-huang/HiRAG)\]\[[RAG-Challenge-2](https://github.com/IlyaRice/RAG-Challenge-2)\]\[[WeKnora](https://github.com/Tencent/WeKnora)\]\[[arXiv Paper Curator](https://github.com/jamwithai/arxiv-paper-curator)\]
      • [paper - RL/PRIME)\]\[[TTRL](https://arxiv.org/abs/2504.16084)\]\[[Free Process Rewards without Process Labels](https://arxiv.org/abs/2412.01981)\]\[[OREAL](https://github.com/InternLM/OREAL)\]\[[VisualPRM](https://arxiv.org/abs/2503.10291)\]\[[Crossing the Reward Bridge](https://arxiv.org/abs/2503.23829)\]\[[GenPRM](https://arxiv.org/abs/2504.00891)\]
      • [paper - nlp/CodeIO)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]
      • [paper - Lancer](https://github.com/openai/SWELancer-Benchmark)\]\[[OpenCodeReasoning](https://arxiv.org/abs/2504.01943)\]\[[OpenCodeReasoning-II](https://arxiv.org/abs/2507.09075)\]\[[AceReason-Nemotron](https://arxiv.org/abs/2505.16400)\]\[[AceReason-Nemotron 1.1](https://arxiv.org/abs/2506.13284)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [paper - Survey)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - rg/recurrent-pretraining)\]\[[ReasonFlux](https://github.com/Gen-Verse/ReasonFlux)\]\[[Can 1B LLM Surpass 405B LLM](https://arxiv.org/abs/2502.06703)\]\[[SkyThought](https://arxiv.org/abs/2502.07374)\]\[[AM-Thinking-v1](https://arxiv.org/abs/2505.08311)\]\[[POLARIS](https://github.com/ChenxinAn-fdu/POLARIS)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [Open-Reasoner-Zero
      • [paper - RL)\]\[[FastCuRL](https://github.com/nick7nlp/FastCuRL)\]\[[SRPO](https://arxiv.org/abs/2504.14286)\]\[[Tina](https://arxiv.org/abs/2504.15777)\]\[[Meta-Ability-Alignment](https://arxiv.org/abs/2505.10554)\]\[[Parallel-R1](https://arxiv.org/abs/2509.07980)\]
      • [paper
      • [paper - AI/SkyThought)\]\[[DeepCoder](https://pretty-radio-b75.notion.site/DeepCoder-A-Fully-Open-Source-14B-Coder-at-O3-mini-Level-1cf81902c14680b3bee5eb349a512a51)\]\[[DeepSWE](https://github.com/agentica-project/rllm/tree/main/examples/swe)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Deep-Research](https://github.com/HKUDS/Auto-Deep-Research)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper
      • [paper
      • [paper - FinAI/Fino1)\]\[[PIXIU](https://github.com/The-FinAI/PIXIU)\]\[[FLAG-Trader](https://arxiv.org/abs/2502.11433)\]\[[FinAudio](https://arxiv.org/abs/2503.20990)\]
      • [paper - PaLM)\]
      • [paper
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [paper - Trustworthy-Retrieval-Augmented-Generation)\]\[[TrustRAG](https://github.com/gomate-community/TrustRAG)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - OR1](https://github.com/SkyworkAI/Skywork-OR1)\]
      • [Moonlight
      • [paper
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - GSAI/LLaDA)\]\[[LLaDA 1.5](https://arxiv.org/abs/2505.19223)\]\[[LLaDA-V](https://arxiv.org/abs/2505.16933)\]\[[SMDM](https://github.com/ML-GSAI/SMDM)\]\[[Diffusion-LLM-Papers](https://github.com/ML-GSAI/Diffusion-LLM-Papers)\]\[[Diffusion-LM](https://github.com/XiangLi1999/Diffusion-LM)\]\[[BD3-LM](https://github.com/kuleshov-group/bd3lms)\]\[[mdlm](https://github.com/kuleshov-group/mdlm)\]\[[Dream](https://github.com/DreamLM/Dream)\]\[[DiffuLLaMA](https://github.com/HKUNLP/DiffuLLaMA)\]\[[d1](https://github.com/dllm-reasoning/d1)\]\[[Gemini Diffusion](https://deepmind.google/models/gemini-diffusion/)\]\[[MMaDA](https://github.com/Gen-Verse/MMaDA)\]\[[dLLM-RL](https://github.com/Gen-Verse/dLLM-RL)\]\[[LaViDa](https://github.com/jacklishufan/LaViDa)\]\[[Diffusion vs. Autoregressive Language Models](https://arxiv.org/abs/2505.15045)\]\[[DLLM-Survey](https://github.com/LiQiiiii/DLLM-Survey)\]\[[dKV-Cache](https://arxiv.org/abs/2505.15781)\]\[[dLLM-cache](https://github.com/maomaocun/dLLM-cache)\]\[[Fast-dLLM](https://github.com/NVlabs/Fast-dLLM)\]\[[dInfer](https://github.com/inclusionAI/dInfer)\]\[[Seed Diffusion](https://arxiv.org/abs/2508.02193)\]\[[SDAR](https://github.com/JetAstra/SDAR)\]\[[Open-dLLM](https://github.com/pengzhangzhi/Open-dLLM)\]\[[LLaDA Pretraining](https://github.com/Auraithm/LLADA_pretraining)\]\[[dllm-trainer](https://github.com/ZHZisZZ/dllm-trainer)\]\[[SDLM](https://github.com/OpenGVLab/SDLM)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper
      • [paper
      • [paper - rewarding-reasoning-LLM)\]
      • [paper - PaLM)\]
      • [paper
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [blog - agents-python/mcp/)\]\[[mcp-for-beginners](https://github.com/microsoft/mcp-for-beginners)\]\[[How I Finally Understood MCP](https://towardsdatascience.com/how-i-finally-understood-mcp-and-got-it-working-irl-2/)\]\[[fastmcp](https://github.com/jlowin/fastmcp)\]\[[MCP.so](https://mcp.so)\]\[[mcpagents](https://mcpagents.dev)\]\[[ModelScope MCP](https://www.modelscope.cn/mcp)\]\[[mcp-agent](https://github.com/lastmile-ai/mcp-agent)\]\[[awesome-mcp-servers](https://github.com/punkpeye/awesome-mcp-servers)\]\[[Awesome-MCP-ZH](https://github.com/yzfly/Awesome-MCP-ZH)\]\[[mcp](https://github.com/awslabs/mcp)\]\[[ScaleMCP](https://arxiv.org/abs/2505.06416)\]\[[A2A](https://github.com/google/A2A)\]\[[adk-python](https://github.com/google/adk-python)\]\[[MiniMax-MCP](https://github.com/MiniMax-AI/MiniMax-MCP)\]\[[MCP-Universe](https://github.com/SalesforceAIResearch/MCP-Universe)\]\[[MCP-Bench](https://github.com/Accenture/mcp-bench)\]\[[MCPMark](https://github.com/eval-sys/mcpmark)\]
      • [paper - V2](https://github.com/inclusionAI/Ling-V2)\]\[[Ling-Coder-lite](https://arxiv.org/abs/2503.17793)\]\[[Ring-lite](https://arxiv.org/abs/2506.14731)\]\[[Ring-1T](https://arxiv.org/abs/2510.18855)\]\[[Ring-linear](https://arxiv.org/abs/2510.19338)\]\[[DLRover](https://github.com/intelligent-machine-learning/dlrover)\]\[[GroveMoE](https://github.com/inclusionAI/GroveMoE)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper - oryx/Awesome-LLM-Post-training)\]\[[A Survey on Post-training of Large Language Models](https://arxiv.org/abs/2503.06072)\]\[[Sailing AI by the Stars](https://arxiv.org/abs/2505.02686)\]\[[Agentic Reinforcement Learning](https://arxiv.org/abs/2509.02547)\]\[[Awesome-RL-for-LRMs](https://arxiv.org/abs/2509.08827)\]\[[Unify-Post-Training](https://arxiv.org/abs/2509.04419)\]\[[Post-training 101](https://tokens-for-thoughts.notion.site/post-training-101)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - Searcher)\]\[[R1-Searcher++](https://arxiv.org/abs/2505.17005)\]\[[SimpleDeepSearcher](https://github.com/RUCAIBox/SimpleDeepSearcher)\]\[[Search-o1](https://github.com/sunnynexus/Search-o1)\]\[[WebThinker](https://github.com/RUC-NLPIR/WebThinker)\]\[[ReSearch](https://github.com/Agent-RL/ReCall)\]\[[Auto-Deep-Research](https://github.com/HKUDS/Auto-Deep-Research)\]\[[deep-searcher](https://github.com/zilliztech/deep-searcher)\]
      • [paper - law/steplaw)\]\[[ParScale](https://arxiv.org/abs/2505.10475)\]\[[The Art of Scaling Reinforcement Learning Compute for LLMs](https://arxiv.org/abs/2510.13786)\]\[[Scaling Latent Reasoning via Looped Language Models](https://arxiv.org/abs/2510.25741)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [blog - 3n-685065323f5984ef315c93f4)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [blog - agents-python)\]\[[openai-cua-sample-app](https://github.com/openai/openai-cua-sample-app)\]\[[swarm](https://github.com/openai/swarm)\]\[[A practical guide to building agents](https://cdn.openai.com/business-guides-and-resources/a-practical-guide-to-building-agents.pdf)\]\[[Customer Service Agents Demo](https://github.com/openai/openai-cs-agents-demo)\]\[[adk-python](https://github.com/google/adk-python)\]\[[agents-deep-research](https://github.com/qx-labs/agents-deep-research)\]\[[Building effective agents](https://www.anthropic.com/research/building-effective-agents)\]\[[Writing effective tools for agents](https://www.anthropic.com/engineering/writing-tools-for-agents)\]\[[How we built our multi-agent research system](https://www.anthropic.com/engineering/built-multi-agent-research-system)\]\[[Don't Build Multi-Agents](https://cognition.ai/blog/dont-build-multi-agents)\]\[[Context Engineering for AI Agents](https://manus.im/blog/Context-Engineering-for-AI-Agents-Lessons-from-Building-Manus)\]\[[Context Engineering](https://blog.langchain.com/context-engineering-for-agents/)\]\[[Effective context engineering for AI agents](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents)\]\[[Building agents with the Claude Agent SDK](https://www.anthropic.com/engineering/building-agents-with-the-claude-agent-sdk)\]\[[Agent Skills](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]
      • [paper
      • [paper
      • [paper - R1)\]\[[DeepRetrieval](https://github.com/pat-jj/DeepRetrieval)\]\[[s3](https://github.com/pat-jj/s3)\]\[[DeepResearcher](https://github.com/GAIR-NLP/DeepResearcher)\]\[[ZeroSearch](https://github.com/Alibaba-NLP/ZeroSearch)\]\[[IKEA](https://arxiv.org/abs/2505.07596)\]\[[LeReT](https://github.com/sher222/LeReT)\]\[[MMSearch-R1](https://github.com/EvolvingLMMs-Lab/multimodal-search-r1)\]\[[ASearcher](https://github.com/inclusionAI/ASearcher)\]\[[MiroThinker](https://github.com/MiroMindAI/MiroThinker)\]\[[PokeeResearchOSS](https://github.com/Pokee-AI/PokeeResearchOSS)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper - infra-index](https://github.com/deepseek-ai/open-infra-index)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - ai/VisualThinker-R1-Zero)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[R1-VL](https://github.com/jingyi0000/R1-VL)\]\[[R1-Omni](https://github.com/HumanMLLM/R1-Omni)\]\[[Vision-R1](https://github.com/Osilly/Vision-R1)\]\[[Open-R1-Video](https://github.com/Wang-Xiaodong1899/Open-R1-Video)\]\[[OpenVLThinker](https://github.com/yihedeng9/OpenVLThinker)\]\[[R1-Zero-VSI](https://github.com/zhijie-group/R1-Zero-VSI)\]\[[VLAA-Thinking](https://github.com/UCSC-VLAA/VLAA-Thinking)\]\[[RL-with-Cold-Start](https://github.com/waltonfuture/RL-with-Cold-Start)\]\[[Revisual-R1](https://github.com/CSfufu/Revisual-R1)\]\[[SophiaVL-R1](https://github.com/kxfan2002/SophiaVL-R1)\]\[[NoisyRollout](https://github.com/John-AI-Lab/NoisyRollout)\]\[[VisuLogic-Train](https://github.com/VisuLogic-Benchmark/VisuLogic-Train)\]\[[OpenThinkIMG](https://github.com/zhaochen0110/OpenThinkIMG)\]\[[VisionReasoner](https://github.com/dvlab-research/VisionReasoner)\]\[[DeepEyes](https://github.com/Visual-Agent/DeepEyes)\]\[[VisualPlanning](https://github.com/yix8/VisualPlanning)\]\[[Thinking with Generated Images](https://github.com/GAIR-NLP/thinking-with-generated-images)\]\[[GRIT](https://github.com/eric-ai-lab/GRIT)\]\[[VTool-R1](https://github.com/VTool-R1/VTool-R1)\]\[[Thinking with Images for Multimodal Reasoning](https://github.com/zhaochen0110/Awesome_Think_With_Images)\]\[[Thyme](https://github.com/yfzhang114/Thyme)\]\[[Mini-o3](https://github.com/Mini-o3/Mini-o3)\]
      • [paper - r1)\]\[[MM-EUREKA](https://github.com/ModalMinds/MM-EUREKA)\]\[[Vision-R1](https://arxiv.org/abs/2503.18013)\]\[[Perception-R1](https://github.com/linkangheng/PR1)\]\[[VisionThink](https://github.com/dvlab-research/VisionThink)\]\[[MMR1](https://github.com/LengSicong/MMR1)\]
      • [Agent-R1 - AI/RAGEN)\]\[[VAGEN](https://github.com/RAGEN-AI/VAGEN)\]\[[OpenManus-RL](https://github.com/OpenManus/OpenManus-RL)\]\[[SWEET-RL](https://arxiv.org/abs/2503.15478)\]\[[APIGen-MT](https://arxiv.org/abs/2504.03601)\]
      • [paper - Long-Chain-of-Thought-Reasoning)\]\[[Awesome-System2-Reasoning-LLM](https://github.com/zzli2022/Awesome-System2-Reasoning-LLM)\]\[[Stop Overthinking](https://arxiv.org/abs/2503.16419)\]\[[Awesome_Efficient_LRM_Reasoning](https://github.com/XiaoYee/Awesome_Efficient_LRM_Reasoning)\]\[[A Survey on Test-Time Scaling in Large Language Models](https://arxiv.org/abs/2503.24235)\]\[[Awesome-RL-Reasoning-Recipes](https://github.com/TsinghuaC3I/Awesome-RL-Reasoning-Recipes)\]\[[Generative AI Act II](https://arxiv.org/abs/2504.13828)\]\[[100 Days After DeepSeek-R1](https://arxiv.org/abs/2505.00551)\]\[[A Sober Look at Progress in Language Model Reasoning](https://arxiv.org/abs/2504.07086)\]\[[Awesome-RL-for-LRMs](https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - GR00T)\]\[[IsaacLab](https://github.com/isaac-sim/IsaacLab)\]\[[IsaacGymEnvs](https://github.com/isaac-sim/IsaacGymEnvs)\]\[[OmniIsaacGymEnvs](https://github.com/isaac-sim/OmniIsaacGymEnvs)\]\[[MuJoCo Playground](https://playground.mujoco.org)\]\[[DreamGen](https://arxiv.org/abs/2505.12705)\]\[[MimicGen](https://github.com/NVlabs/mimicgen)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]
      • [paper
      • [paper
      • [paper - AIFLM-Lab/Fin-R1)\]\[[FinRL-DeepSeek](https://github.com/benstaf/FinRL_DeepSeek)\]\[[DianJin-R1](https://arxiv.org/abs/2504.15716)\]\[[Recon](https://github.com/MasterZhou1/Recon)\]\[[FinChain](https://github.com/mbzuai-nlp/finchain)\]\[[Agentar-Fin-R1](https://arxiv.org/abs/2507.16802)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper - ai-lab/LookaheadDecoding)\]\[[Consistency_LLM](https://github.com/hao-ai-lab/Consistency_LLM)\]\[[Lookahead](https://github.com/alipay/PainlessInferenceAcceleration)\]
      • [blog - PD](https://github.com/infinigence/Semi-PD)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [trt-llm-rag-windows - crawler](https://github.com/BuilderIO/gpt-crawler)\]\[[R2R](https://github.com/SciPhi-AI/R2R)\]\[[rag-notebook-to-microservices](https://github.com/wenqiglantz/rag-notebook-to-microservices)\]\[[MaxKB](https://github.com/1Panel-dev/MaxKB)\]\[[Verba](https://github.com/weaviate/Verba)\]\[[cognita](https://github.com/truefoundry/cognita)\]\[[llmware](https://github.com/llmware-ai/llmware)\]\[[quivr](https://github.com/QuivrHQ/quivr)\]\[[kotaemon](https://github.com/Cinnamon/kotaemon)\]\[[RAGMeUp](https://github.com/AI-Commandos/RAGMeUp)\]\[[pandas-ai](https://github.com/sinaptik-ai/pandas-ai)\]\[[DeepSeek-RAG-Chatbot](https://github.com/SaiAkhil066/DeepSeek-RAG-Chatbot)\]
      • [paper - nlp/simpleRL-reason)\]\[[CodeIO](https://github.com/hkust-nlp/CodeIO)\]\[[Laser](https://github.com/hkust-nlp/Laser)\]\[[B-STaR](https://arxiv.org/abs/2412.17256)\]\[[General-Reasoner](https://github.com/TIGER-AI-Lab/General-Reasoner)\]
      • [paper
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]
      • [paper
      • [paper
      • [paper - agi/OpenDeepSearch)\]\[[Recursive Open Meta-Agents](https://github.com/sentient-agi/ROMA)\]\[[deep-searcher](https://github.com/zilliztech/deep-searcher)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [The Effect of Prompt Tokens on Instruction Tuning
      • [paper
      • [paper - RL/ReCall)\]\[[Synergizing RAG and Reasoning](https://arxiv.org/abs/2504.15909)\]\[[Agentic-RAG-R1](https://github.com/jiangxinke/Agentic-RAG-R1)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - R1)\]\[[SEED-Bench-R1](https://github.com/TencentARC/SEED-Bench-R1)\]\[[Open-R1-Video](https://github.com/Wang-Xiaodong1899/Open-R1-Video)\]\[[TinyLLaVA-Video-R1](https://github.com/ZhangXJ199/TinyLLaVA-Video-R1)\]\[[Video-Holmes](https://github.com/TencentARC/Video-Holmes)\]
      • [DeepSpeed - us/research/blog/zero-deepspeed-new-system-optimizations-enable-training-models-with-over-100-billion-parameters/)\]
      • [DeepSpeed-MII - FastGen](https://github.com/microsoft/DeepSpeed/tree/master/blogs/deepspeed-fastgen)\]\[[ONNX Runtime](https://github.com/microsoft/onnxruntime)\]\[[onnx](https://github.com/onnx/onnx)\]\[[Nanoflow](https://github.com/efeslab/Nanoflow)\]
      • [paper - BandAI/ReportBench)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - Reasoner-Zero/Open-Reasoner-Zero)\]\[[Skywork-OR1](https://github.com/SkyworkAI/Skywork-OR1)\]\[[One-Shot-RLVR](https://github.com/ypwang61/One-Shot-RLVR)\]\[[Absolute-Zero-Reasoner](https://github.com/LeapLabTHU/Absolute-Zero-Reasoner)\]\[[R-Zero](https://github.com/Chengsong-Huang/R-Zero)\]\[[Negative-aware Fine-Tuning](https://arxiv.org/abs/2505.18116)\]\[[RLPR](https://github.com/openbmb/RLPR)\]
      • [blog - models](https://github.com/meta-llama/llama-models)\]\[[J1](https://arxiv.org/abs/2505.10320)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [Seed-Thinking-v1.5 - 4-reasoning Technical Report](https://arxiv.org/abs/2504.21318)\]\[[Llama-Nemotron: Efficient Reasoning Models](https://arxiv.org/abs/2505.00949)\]
      • [paper - ultra](https://github.com/pangu-tech/pangu-ultra)\]\[[Pangu Ultra MoE](https://arxiv.org/abs/2505.04519)\]\[[Pangu Pro MoE](https://arxiv.org/abs/2505.21411)\]\[[pangu-pro-moe](https://gitcode.com/ascend-tribe/pangu-pro-moe)\]\[[Pangu Light](https://arxiv.org/abs/2505.20155)\]\[[Pangu Embedded](https://arxiv.org/abs/2505.22375)\]\[[triton-ascend](https://github.com/Ascend/triton-ascend)\]\[[PreMoe](https://arxiv.org/abs/2505.17639)\]\[[Pangu DeepDiver](https://arxiv.org/abs/2505.24332)\]\[[Serving Large Language Models on Huawei CloudMatrix384](https://arxiv.org/abs/2506.12708)\]\[[xDeepServe](https://arxiv.org/abs/2508.02520)\]\[[ascend-training-system](https://gitcode.com/ascend-tribe/ascend-training-system)\]\[[ascend-inference-cluster](https://gitcode.com/ascend-tribe/ascend-inference-cluster)\]\[[ascend-inference-system](https://gitcode.com/ascend-tribe/ascend-inference-system)\]\[[AsyncFlow](https://gitee.com/ascend/MindSpeed-RL)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - ai-lab/VLM-R1)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]
      • [paper - VL)\]\[[Moonlight](https://github.com/MoonshotAI/Moonlight)\]\[[APOLLO](https://github.com/zhuhanqing/APOLLO)\]\[[Kimi K2](https://arxiv.org/abs/2507.20534)\]\[[Kimi-Linear](https://github.com/MoonshotAI/Kimi-Linear)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]
      • [paper
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper
      • [paper - NLP/ToRL)\]\[[ReCall](https://github.com/Agent-RL/ReCall)\]\[[ReTool](https://arxiv.org/abs/2504.11536)\]\[[ToolRL](https://arxiv.org/abs/2504.13958)\]\[[OTC](https://arxiv.org/abs/2504.14870)\]\[[Improving Multi-Turn Tool Use with RL](https://www.bespokelabs.ai/blog/improving-multi-turn-tool-use-with-reinforcement-learning)\]\[[OpenThinkIMG](https://github.com/zhaochen0110/OpenThinkIMG)\]\[[VTool-R1](https://github.com/VTool-R1/VTool-R1)\]\[[Tool-Star](https://github.com/RUC-NLPIR/Tool-Star)\]\[[Tool-N1](https://github.com/NVlabs/Tool-N1)\]\[[ZeroTIR](https://arxiv.org/abs/2505.07773)\]\[[VerlTool](https://github.com/TIGER-AI-Lab/verl-tool)\]\[[ARPO](https://github.com/RUC-NLPIR/ARPO)\]\[[Tool-Star](https://github.com/RUC-NLPIR/Tool-Star)\]\[[Understanding Tool-Integrated Reasoning](https://arxiv.org/abs/2508.19201)\]\[[SimpleTIR](https://github.com/ltzheng/SimpleTIR)\]\[[AgentFlow](https://github.com/lupantech/AgentFlow)\]
      • [blog - pytorch-fully-sharded-data-parallel-api/)\]\[[pytorch-fsdp](https://github.com/huggingface/blog/blob/main/zh/pytorch-fsdp.md)\]
      • [paper
      • [paper - Learning-Enhanced-LLMs-A-Survey)\]
      • [paper - guidebook](https://github.com/huggingface/evaluation-guidebook)\]\[[xbench-evals](https://github.com/xbench-ai/xbench-evals)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [OpenDevin - code-rover](https://github.com/nus-apr/auto-code-rover)\]\[[developer](https://github.com/smol-ai/developer)\]\[[aider](https://github.com/paul-gauthier/aider)\]\[[claude-engineer](https://github.com/Doriandarko/claude-engineer)\]\[[SuperCoder](https://github.com/TransformerOptimus/SuperCoder)\]\[[AIDE](https://github.com/WecoAI/aideml)\]\[[vulnhuntr](https://github.com/protectai/vulnhuntr)\]\[[devin.cursorrules](https://github.com/grapeot/devin.cursorrules)\]\[[DeepSeek Engineer](https://github.com/Doriandarko/deepseek-engineer)\]\[[DeepCode](https://github.com/HKUDS/DeepCode)\]\[[Online RL for Cursor Tab](https://cursor.com/en/blog/tab-rl)\]
      • [Qwen3
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - ai/letta)\]\[[Agent Workflow Memory](https://github.com/zorazrw/agent-workflow-memory)\]\[[A-mem](https://github.com/agiresearch/A-mem)\]\[[Rethinking Memory in AI](https://arxiv.org/abs/2505.00675)\]\[[Memvid](https://github.com/Olow304/memvid)\]\[[Memory OS](https://github.com/BAI-LAB/MemoryOS)\]\[[Awesome AI Memory](https://github.com/topoteretes/awesome-ai-memory)\]\[[MemAgent](https://github.com/BytedTsinghua-SIA/MemAgent)\]\[[MemOS](https://github.com/MemTensor/MemOS)\]\[[MIRIX](https://github.com/Mirix-AI/MIRIX)\]\[[memU](https://github.com/NevaMind-AI/memU)\]\[[LangMem](https://github.com/langchain-ai/langmem)\]\[[memori](https://github.com/GibsonAI/memori)\]\[[A-MEM](https://github.com/WujiangXu/A-mem)\]\[[LongMemEval](https://github.com/xiaowu0162/LongMemEval)\]\[[LightMem](https://github.com/zjunlp/LightMem)\]
      • [paper
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]
      • [paper
      • [paper
      • [paper - NLPIR/WebThinker)\]\[[DeepAgent](https://github.com/RUC-NLPIR/DeepAgent)\]\[[AgentFamily](https://github.com/RUC-NLPIR/AgentFamily)\]\[[Chain-of-Agents](https://arxiv.org/abs/2508.13167)\]
      • [paper - R1](https://github.com/ielab/llm-rankers/tree/main/Rank-R1)\]\[[Rearank](https://arxiv.org/abs/2505.20046)\]\[[TongSearch-QR](https://arxiv.org/abs/2506.11603)\]\[[ReasonRank](https://github.com/8421BCD/ReasonRank)\]\[[BGE_Reasoner](https://github.com/FlagOpen/FlagEmbedding/tree/38f4bbf528c942724eeca9f694db5c9fe7513905/research/BGE_Reasoner)\]
      • [paper - Skills)\]\[[AI Mathematical Olympiad-Progress Prize 2](https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2)\]\[[9th Place Solution](https://github.com/analokmaus/kaggle-aimo2-fast-math-r1)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - R1V)\]\[[Skywork R1V2](https://arxiv.org/abs/2504.16656)\]\[[Skywork-R1V3](https://arxiv.org/abs/2507.06167)\]\[[Skywork-VL Reward](https://arxiv.org/abs/2505.07263)\]
      • [paper - lab-nu/RAGEN)\]\[[VAGEN](https://github.com/mll-lab-nu/VAGEN)\]\[[Agent-R1](https://github.com/0russwest0/Agent-R1)\]\[[OpenManus-RL](https://github.com/OpenManus/OpenManus-RL)\]\[[SWEET-RL](https://arxiv.org/abs/2503.15478)\]\[[APIGen-MT](https://arxiv.org/abs/2504.03601)\]\[[ARTIST](https://arxiv.org/abs/2505.01441)\]\[[SkyRL](https://github.com/NovaSky-AI/SkyRL)\]\[[Visual-ARFT](https://arxiv.org/abs/2505.14246)\]\[[verl-agent](https://github.com/langfengQ/verl-agent)\]\[[Awesome-Agent-RL](https://github.com/0russwest0/Awesome-Agent-RL)\]\[[SPA-RL-Agent](https://github.com/WangHanLinHenry/SPA-RL-Agent)\]\[[Multi-Turn-RL-Agent](https://github.com/SiliangZeng/Multi-Turn-RL-Agent)\]\[[MARTI](https://github.com/TsinghuaC3I/MARTI)\]\[[AgentsMeetRL](https://github.com/thinkwee/AgentsMeetRL)\]\[[L0](https://github.com/cmriat/l0)\]\[[ARPO](https://github.com/RUC-NLPIR/ARPO)\]\[[Cognitive Kernel-Pro](https://github.com/Tencent/CognitiveKernel-Pro)\]\[[Agent Lightning](https://github.com/microsoft/agent-lightning)\]\[[Agent Reinforcement Trainer](https://github.com/OpenPipe/ART)\]\[[Memento](https://github.com/Agent-on-the-Fly/Memento)\]\[[AgentGym-RL](https://github.com/woooodyy/AgentGym-RL)\]\[[Tree-GRPO](https://github.com/AMAP-ML/Tree-GRPO)\]\[[Pipeline RL](https://github.com/ServiceNow/pipelinerl)\]\[[AgentRL](https://github.com/THUDM/AgentRL)\]\[[GEM](https://github.com/axon-rl/gem)\]
      • [paper - health/uqlm)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]
      • [paper
      • [Seed-Coder
      • [blog - ai/Kevin-32B)\]\[[deepwiki](https://cognition.ai/blog/deepwiki)\]\[[deepwiki-open](https://github.com/AsyncFuncAI/deepwiki-open)\]\[[AI Documentation Generator](https://github.com/divar-ir/ai-doc-gen)\]
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - bench)\]
      • [paper - Seed/Seed-Coder)\]\[[CURE](https://arxiv.org/abs/2506.03136)\]\[[CodeContests+](https://arxiv.org/abs/2506.05817)\]\[[Kimi-Dev](https://github.com/MoonshotAI/Kimi-Dev)\]
      • [paper - VL](https://github.com/XiaomiMiMo/MiMo-VL)\]\[[Rollout Routing Replay](https://arxiv.org/abs/2510.11370)\]
      • [paper - Seed/Seed-Thinking-v1.5)\]\[[Hunyuan-TurboS](https://arxiv.org/abs/2505.15431)\]\[[MiniMax-M1](https://arxiv.org/abs/2506.13585)\]\[[Step3](https://github.com/stepfun-ai/Step3)\]\[[GLM-4.5V and GLM-4.1V-Thinking](https://arxiv.org/abs/2507.01006)\]\[[Kwai Keye-VL 1.5](https://arxiv.org/abs/2509.01563)\]\[[Phi-4-reasoning Technical Report](https://arxiv.org/abs/2504.21318)\]\[[Llama-Nemotron: Efficient Reasoning Models](https://arxiv.org/abs/2505.00949)\]\[[Magistral](https://arxiv.org/abs/2506.10910)\]\[[Xiaomi MiMo](https://arxiv.org/abs/2505.07608)\]\[[Skywork-OR1](https://arxiv.org/abs/2505.22312)\]\[[Ring-lite](https://arxiv.org/abs/2506.14731)\]\[[XBai-o4](https://github.com/MetaStone-AI/XBai-o4)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Zero](https://github.com/xfey/MCP-Zero)\]\[[Self-Evolving-Agents](https://arxiv.org/abs/2507.21046)\]\[[GEM](https://github.com/axon-rl/gem)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - GSAI/YuLan-OneSim)\]\[[Social_Science](https://github.com/RenqiChen/Social_Science)\]\[[SocialAgent](https://github.com/FudanDISC/SocialAgent)\]\[[game_theory](https://github.com/Wenyueh/game_theory)\]\[[LLM-Economist](https://github.com/sethkarten/LLM-Economist)\]
      • [paper
      • [paper - NLP/ZeroSearch)\]\[[MaskSearch](https://arxiv.org/abs/2505.20285)\]\[[OmniSearch](https://github.com/Alibaba-NLP/OmniSearch)\]\[[WebAgent](https://github.com/Alibaba-NLP/DeepResearch)\]\[[VRAG-RL](https://github.com/Alibaba-NLP/VRAG)\]\[[SSRL](https://github.com/TsinghuaC3I/SSRL)\]
      • [paper - PaLM)\]
      • [paper - AI/SynLogic)\]\[[Synthetic Data RL](https://arxiv.org/abs/2505.17063)\]\[[SynthRL](https://github.com/NUS-TRAIL/SynthRL)\]\[[Loong](https://arxiv.org/abs/2509.03059)\]\[[Webscale-RL Data Pipeline](https://github.com/SalesforceAIResearch/PretrainRL-pipeline)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper - MoE)\]\[[MiniMax-01](https://arxiv.org/abs/2501.08313)\]\[[Hunyuan-TurboS](https://arxiv.org/abs/2505.15431)\]\[[MiniMax-M1](https://arxiv.org/abs/2506.13585)\]\[[Ring-lite](https://arxiv.org/abs/2506.14731)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - ucb/Intuitor)\]\[[Entropy-Mechanism-of-RL](https://arxiv.org/abs/2505.22617)\]\[[One-shot Entropy Minimization](https://arxiv.org/abs/2505.20282)\]\[[RL-Without-GT](https://arxiv.org/abs/2505.19439)\]\[[VeriFree](https://arxiv.org/abs/2505.21493)\]\[[Spurious Rewards](https://github.com/ruixin31/Rethink_RLVR)\]\[[Reasoning Pattern Reward](https://github.com/trestad/Noisy-Rewards-in-Learning-to-Reason)\]\[[high-entropy-minority-tokens-rlvr](https://arxiv.org/abs/2506.01939)\]\[[Energy-Based Transformers](https://github.com/alexiglad/ebt)\]\[[Hierarchical Reasoning Model](https://github.com/sapientinc/HRM)\]\[[DeepConf](https://arxiv.org/abs/2508.15260)\]
      • [blog - Next](https://qwen.ai/blog?id=4074cca80393150c248e508aa62983f9cb7d27cd&from=research.latest-advancements-list)\]\[[Qwen3-Embedding](https://github.com/QwenLM/Qwen3-Embedding)\]\[[WorldPM](https://github.com/QwenLM/WorldPM)\]\[[QwenLong-L1](https://arxiv.org/abs/2505.17667)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - diffucoder)\]\[[Mercury](https://arxiv.org/abs/2506.17298)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - ai/owl)\]\[[AgentOrchestra](https://arxiv.org/abs/2506.12508)\]\[[Eigent](https://github.com/eigent-ai/eigent)\]\[[Agent World](https://github.com/inclusionAI/AWorld)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - R1](https://github.com/TauricResearch/Trading-R1)\]\[[Qlib](https://github.com/microsoft/qlib)\]\[[AI Hedge Fund](https://github.com/virattt/ai-hedge-fund)\]\[[TradingAgents-CN](https://github.com/hsliuping/TradingAgents-CN)\]\[[QuantAgent](https://github.com/y-research-sbu/QuantAgent)\]\[[ValueCell](https://github.com/ValueCell-ai/valuecell)\]\[[Alpha Arena](https://nof1.ai/)\]\[[ROCKFLOW RockAlpha](https://rockalpha.rockflow.ai/)\]\[[AI-Trader](https://github.com/HKUDS/AI-Trader)\]\[[AI AGENTS FOR TRADING](https://github.com/moondevonyt/moon-dev-ai-agents)\]
      • [paper - PaLM)\]
      • [paper - M1](https://github.com/baichuan-inc/Baichuan-M1-14B)\]\[[Baichuan-M2-32B](https://github.com/baichuan-inc/Baichuan-M2-32B)\]\[[MedGemma](https://arxiv.org/abs/2507.05201)\]
      • [paper - Zero)\]
      • [paper - YATT](https://arxiv.org/abs/2508.07970)\]
      • [paper - ZH-HQ-Classifiers](https://huggingface.co/BAAI/CCI4.0-ZH-HQ-Classifiers)\]\[[CCI3.0-HQ](https://arxiv.org/abs/2410.18505)\]
      • [paper - thought/reasoning-gym)\]
      • [paper - thoughts/open-thoughts)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [paper - Embedding)\]
      • [blog - VL](https://github.com/baidubce/Qianfan-VL)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [Kimi-K2 - K2/)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - X0](https://github.com/FlagOpen/RoboBrain-X0)\]\[[RoboOS](https://github.com/FlagOpen/RoboOS)\]\[[GR-3 Technical Report](https://arxiv.org/abs/2507.15493)\]\[[Robix](https://arxiv.org/abs/2509.01106)\]\[[RLinf](https://github.com/RLinf/RLinf)\]\[[WALL-OSS](https://github.com/X-Square-Robot/wall-x)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [GLM-4.5 - 4.5)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [blog - Coder](https://github.com/QwenLM/Qwen3-Coder)\]\[[Qwen Code](https://github.com/QwenLM/qwen-code)\]\[[qwen-code-action](https://github.com/QwenLM/qwen-code-action)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - PaLM)\]
      • [paper - NLP/MegaScience)\]
      • [paper - Seed/EvaLearn)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [paper - Context-Engineering)\]\[[Context Engineering](https://github.com/davidkimai/Context-Engineering)\]\[[Context Engineering Template](https://github.com/coleam00/context-engineering-intro)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [gpt-oss - 2 to gpt-oss](https://sebastianraschka.com/blog/2025/from-gpt-2-to-gpt-oss.html)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - PaLM)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [paper - PaLM)\]
      • [Seed-OSS - Flash-Chat](https://github.com/meituan-longcat/LongCat-Flash-Chat)\]\[[Skywork](https://github.com/SkyworkAI/Skywork)\]\[[Skywork-MoE](https://github.com/SkyworkAI/Skywork-MoE)\]\[[Orion](https://github.com/OrionStarAI/Orion)\]\[[BELLE](https://github.com/LianjiaTech/BELLE)\]\[[Yuan-2.0](https://github.com/IEIT-Yuan/Yuan-2.0)\]\[[Yuan2.0-M32](https://github.com/IEIT-Yuan/Yuan2.0-M32)\]\[[Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM)\]\[[Index-1.9B](https://github.com/bilibili/Index-1.9B)\]\[[dots.llm1](https://github.com/rednote-hilab/dots.llm1)\]\[[dots.vlm1](https://github.com/rednote-hilab/dots.vlm1)\]\[[Aquila2](https://github.com/FlagAI-Open/Aquila2)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - seed/m3-agent)\]\[[WebExplorer](https://github.com/hkust-nlp/WebExplorer)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - S1)\]\[[SciReason](https://github.com/open-sciencelab/SciReason)\]\[[FlowSearch](https://github.com/Alpha-Innovator/InternAgent)\]\[[Chem-R](https://github.com/davidweidawang/Chem-R)\]\[[Awesome-Agent-Scientists](https://github.com/AgenticScience/Awesome-Agent-Scientists)\]\[[Awesome-Scientific-Datasets-and-LLMs](https://github.com/open-sciencelab/Awesome-Scientific-Datasets-and-LLMs)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - Seed/VeOmni)\]
      • [paper - Seed/WideSearch)\]\[[FutureX](https://arxiv.org/abs/2508.11987)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [blog - K2)\]\[[GLM-4.5](https://arxiv.org/abs/2508.06471)\]\[[The Big LLM Architecture Comparison](https://sebastianraschka.com/blog/2025/the-big-llm-architecture-comparison.html)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [paper
      • [blog - org/GLM-4.5)\]\[[GLM-V](https://github.com/zai-org/GLM-V)\]\[[GLM-4.6](https://z.ai/blog/glm-4.6)\]
      • [paper - Nemotron)\]\[[NVIDIA Nemotron Nano 2](https://arxiv.org/abs/2508.14444)\]\[[Nemotron Nano](https://huggingface.co/collections/nvidia/nvidia-nemotron-689f6d6e6ead8e77dd641615)\]\[[Small Language Models are the Future of Agentic AI](https://arxiv.org/abs/2506.02153)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [blog
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [blog - machines-lab/batch_invariant_ops)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [blog - NLP/DeepResearch)\]\[[DeerFlow](https://github.com/bytedance/deer-flow)\]\[[Co-Sight](https://github.com/ZTE-AICloud/Co-Sight)\]\[[Youtu-Agent](https://github.com/TencentCloudADP/youtu-agent)\]\[[Deep Agents](https://github.com/langchain-ai/deepagents)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - coder/Kronos)\]\[[OpenBB](https://github.com/OpenBB-finance/OpenBB)\]
      • [OneRec Technical Report - V2 Technical Report](https://arxiv.org/abs/2508.20900)\]\[[OneRec](https://arxiv.org/abs/2502.18965)\]\[[OneSearch](https://arxiv.org/abs/2509.03236)\]\[[MTGR](https://arxiv.org/abs/2505.18654)\]\[[MTGR blog](https://tech.meituan.com/2025/05/19/meituan-generative-recommendation.html)\]
      • [paper
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper
      • [paper - deepmind/limit)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [blog - nanogpt](https://github.com/KellerJordan/modded-nanogpt)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [blog - Coder](https://github.com/QwenLM/Qwen3-Coder)\]\[[Qwen Code](https://github.com/QwenLM/qwen-code)\]\[[qwen-code-action](https://github.com/QwenLM/qwen-code-action)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [code
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [torchtune - pytorch/torchforge)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [open-interpreter
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper
      • [paper - Efficient/RL-Factory)\]\[[SWEET-RL](https://github.com/facebookresearch/sweet_rl)\]\[[TARL](https://arxiv.org/abs/2509.14480)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [ggml - ai/ktransformers)\]\[[gpt-fast](https://github.com/pytorch-labs/gpt-fast)\]\[[fastllm](https://github.com/ztxz16/fastllm)\]\[[CTranslate2](https://github.com/OpenNMT/CTranslate2)\]\[[ipex-llm](https://github.com/intel-analytics/ipex-llm)\]\[[rtp-llm](https://github.com/alibaba/rtp-llm)\]\[[KsanaLLM](https://github.com/Tencent/KsanaLLM)\]\[[ppl.nn](https://github.com/OpenPPL/ppl.nn)\]\[[ZhiLight](https://github.com/zhihu/ZhiLight)\]\[[WeChat-TFCC](https://github.com/Tencent/WeChat-TFCC)\]\[[ncnn](https://github.com/Tencent/ncnn)\]\[[AngelSlim](https://github.com/Tencent/AngelSlim)\]\[[llumnix](https://github.com/AlibabaPAI/llumnix)\]\[[dash-infer](https://github.com/modelscope/dash-infer)\]\[[truss](https://github.com/basetenlabs/truss)\]\[[chitu](https://github.com/thu-pacman/chitu)\]\[[Tiny LLM](https://github.com/skyzh/tiny-llm)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [paper
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [Advanced RAG Techniques: an Illustrated Overview - RAG-Agent](https://github.com/NirDiamant/Controllable-RAG-Agent)\]\[[GenAI_Agents](https://github.com/NirDiamant/GenAI_Agents)\]\[[Agents Towards Production](https://github.com/NirDiamant/agents-towards-production)\]\[[bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)\]\[[GenAI-Showcase](https://github.com/mongodb-developer/GenAI-Showcase)\]\[[All RAG Techniques](https://github.com/FareedKhan-dev/all-rag-techniques)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [paper
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper - ai/DeepSeek-V3.2-Exp)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper
      • [paper
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [paper
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [paper
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [blog
      • [paper - jj/Awesome-Adaptation-of-Agentic-AI)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper
      • [paper
      • [paper - VLM](https://arxiv.org/abs/2512.04032)\]
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - agent)\]\[[Training-Free GRPO](https://arxiv.org/abs/2510.08191)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper
      • [paper
      • [blog - machines-lab/tinker-cookbook/tree/main/tinker_cookbook/distillation)\]
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper
      • [paper - VL-Embedding)\]
      • [paper - ai/PaCoRe)\]\[[JacobiForcing](https://github.com/hao-ai-lab/JacobiForcing)\]\[[Native Parallel Reasoner](https://github.com/bigai-nlco/Native-Parallel-Reasoner)\]\[[Parallel-R1](https://github.com/zhengkid/Parallel-R1)\]\[[ThreadWeaver](https://github.com/facebookresearch/threadweaver)\]\[[LongCat-Flash-Thinking-2601](https://github.com/meituan-longcat/LongCat-Flash-Thinking-2601)\]
      • [paper - deepmind/graphcast)\]\[[OpenCastKit](https://github.com/HFAiLab/OpenCastKit)\]\[[GenCast](https://deepmind.google/discover/blog/gencast-predicts-weather-and-the-risks-of-extreme-conditions-with-sota-accuracy/)\]\[[PhiFlow](https://github.com/tum-pbs/PhiFlow)\]\[[cBottle](https://github.com/NVlabs/cBottle)\]\[[PhysicsNeMo](https://github.com/NVIDIA/physicsnemo)\]
      • [paper - TS](https://github.com/PriorLabs/tabpfn-time-series)\]
      • [paper - deepmind/synthid-text)\]\[[watermark-anything](https://github.com/facebookresearch/watermark-anything)\]
      • [paper - Weather)\]\[[arxiv](https://arxiv.org/abs/2211.02556)\]
      • [paper
      • [Numina 1st Place Solution - numina/aimo-progress-prize](https://github.com/project-numina/aimo-progress-prize)\]\[[How NuminaMath Won the 1st AIMO Progress Prize](https://huggingface.co/blog/winning-aimo-progress-prize)\]\[[NuminaMath-7B-TIR](https://huggingface.co/AI-MO/NuminaMath-7B-TIR)\]\[[AI achieves silver-medal standard solving International Mathematical Olympiad problems](https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/)\]\[[Gemini with Deep Think](https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/)\]\[[Gemini 2.5 Deep Think](https://blog.google/products/gemini/gemini-2-5-deep-think/)\]\[[IMO 2025 Problem Solver](https://github.com/lyang36/IMO25)\]\[[AWorld](https://github.com/inclusionAI/AWorld)\]
      • [blog - 1M](https://qwenlm.github.io/blog/qwen2.5-1m)\]\[[QwenLong-CPRS](https://arxiv.org/abs/2505.18092)\]\[[QwenLong-L1](https://arxiv.org/abs/2505.17667)\]\[[QwenLong-L1.5](https://arxiv.org/abs/2512.12967)\]
      • [blog
      • [paper - hallucination-detection](https://github.com/patronus-ai/Lynx-hallucination-detection)\]\[[hallucination_probes](https://github.com/obalcells/hallucination_probes)\]
      • [paper
      • [blog - Augmented Generation for Large Language Models](https://arxiv.org/abs/2409.13385)\]\[[ContextRAG](https://arxiv.org/abs/2502.14759)\]\[[LongRefiner](https://github.com/ignorejjj/LongRefiner)\]
      • [Nature paper - ai/DeepSeek-R1)\]\[[Open-R1](https://github.com/huggingface/open-r1)\]\[[Open RS](https://github.com/knoveleng/open-rs)\]\[[TinyZero](https://github.com/Jiayi-Pan/TinyZero)\]\[[simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)\]\[[Logic-RL](https://github.com/Unakar/Logic-RL)\]\[[DeepScaleR](https://github.com/agentica-project/rllm)\]\[[oat-zero](https://oatllm.notion.site/oat-zero)\]\[[understand-r1-zero](https://github.com/sail-sg/understand-r1-zero)\]\[[X-R1](https://github.com/dhcode-cpp/X-R1)\]\[[nano-aha-moment](https://github.com/McGill-NLP/nano-aha-moment)\]\[[Light-R1](https://github.com/Qihoo360/Light-R1)\]\[[ragen](https://github.com/ZihanWang314/ragen)\]\[[R1-V](https://github.com/StarsfieldAI/R1-V)\]\[[VLM-R1](https://github.com/om-ai-lab/VLM-R1)\]\[[open-r1-multimodal](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)\]\[[R1-Onevision](https://github.com/Fancy-MLLM/R1-Onevision)\]\[[Visual-RFT](https://github.com/Liuziyu77/Visual-RFT)\]\[[VisualThinker-R1-Zero](https://github.com/turningpoint-ai/VisualThinker-R1-Zero)\]\[[the-illustrated-deepseek-r1](https://newsletter.languagemodels.co/p/the-illustrated-deepseek-r1)\]\[[Understanding Reasoning LLMs](https://sebastianraschka.com/blog/2025/understanding-reasoning-llms.html)\]

    • 2. Seq2Seq

    • 1. Word2Vec

  • Multimodal

    • 6. Text2Image

      • [paper - E)\]
      • [paper - ai/ControlNet_Plus_Plus)\]\[[ControlNeXt](https://github.com/dvlab-research/ControlNeXt)\]\[[ControlAR](https://github.com/hustvl/ControlAR)\]\[[OminiControl](https://github.com/Yuanshi9815/OminiControl)\]\[[ROICtrl](https://github.com/showlab/ROICtrl)\]
      • [paper - floyd/IF)\]
      • [paper
      • [paper
      • [paper
      • [paper - alpha/PixArt-alpha)\]
      • [paper - ailab/IP-Adapter)\]\[[ID-Animator](https://github.com/ID-Animator/ID-Animator)\]\[[InstantID](https://github.com/instantX-research/InstantID)\]
      • [paper - Adapter)\]
      • [paper - e-3)\]\[[Glyph-ByT5](https://github.com/AIGText/Glyph-ByT5)\]\[[GPT-ImgEval](https://github.com/PicoTrex/GPT-ImgEval)\]
      • [paper
      • [paper - 2)\]
      • [paper - ML/FluxText)\]
      • [paper - AI/laion-datasets)\]\[[blog](https://laion.ai/blog/laion-5b/)\]\[[laion-coco](https://laion.ai/blog/laion-coco/)\]\[[multimodal_textbook](https://github.com/DAMO-NLP-SG/multimodal_textbook)\]\[[kangas](https://github.com/comet-ml/kangas)\]
      • [paper - DiffusionMaster)\]\[[IterComp](https://github.com/YangLing0818/IterComp)\]
      • [paper - alpha/PixArt-alpha)\]
      • [paper - Creation/Awesome-Controllable-T2I-Diffusion-Models)\]
      • [paper - alpha/PixArt-sigma)\]
      • [paper - NKU/StoryDiffusion)\]\[[AutoStudio](https://github.com/donahowe/AutoStudio)\]\[[story-adapter](https://github.com/UCSC-VLAA/story-adapter)\]
      • [Kolors - Virtual-Try-On](https://huggingface.co/spaces/Kwai-Kolors/Kolors-Virtual-Try-On)\]\[[EVLM: An Efficient Vision-Language Model for Visual Understanding](https://arxiv.org/abs/2407.14177)\]\[[Kwai Keye-VL](https://github.com/Kwai-Keye/Keye)\]
      • [flux - flux](https://github.com/XLabs-AI/x-flux)\]\[[x-flux-comfyui](https://github.com/XLabs-AI/x-flux-comfyui)\]\[[FLUX.1-dev-LoRA](https://huggingface.co/Shakker-Labs/FLUX.1-dev-LoRA-blended-realistic-illustration)\]\[[qwen2vl-flux](https://github.com/erwold/qwen2vl-flux)\]\[[1.58-bit FLUX](https://chenglin-yang.github.io/1.58bit.flux.github.io)\]\[[3DIS](https://github.com/limuloo/3DIS)\]\[[HiDream-I1](https://github.com/HiDream-ai/HiDream-I1)\]
      • [paper
      • [paper - flant5-xxl)\]
      • [paper - Sprint](https://arxiv.org/abs/2503.09641)\]\[[SANA-Video](https://arxiv.org/abs/2509.24695)\]
      • [paper - Image)\]\[[Qwen-Image-Edit](https://huggingface.co/Qwen/Qwen-Image-Edit-2509)\]\[[Qwen VLo](https://qwenlm.github.io/blog/qwen-vlo/)\]
      • [paper - Hunyuan/HunyuanImage-3.0)\]\[[HunyuanImage-2.1](https://github.com/Tencent-Hunyuan/HunyuanImage-2.1)\]\[[DreamOmni2](https://github.com/dvlab-research/DreamOmni2)\]\[[Emu3.5](https://github.com/baaivision/Emu3.5)\]
      • [paper - PromptEnhancer/PromptEnhancer)\]\[[Hunyuan3D-1](https://github.com/Tencent/Hunyuan3D-1)\]\[[Hunyuan3D-2](https://github.com/Tencent/Hunyuan3D-2)\]\[[Hunyuan3D-2.1](https://github.com/Tencent-Hunyuan/Hunyuan3D-2.1)\]\[[Hunyuan3D-Omni](https://github.com/Tencent-Hunyuan/Hunyuan3D-Omni)\]\[[HunyuanWorld-1.0](https://github.com/Tencent-Hunyuan/HunyuanWorld-1.0)\]\[[Hunyuan-Game](https://arxiv.org/abs/2505.14135)\]\[[FlashVDM](https://github.com/Tencent/FlashVDM)\]\[[InstantCharacter](https://github.com/Tencent/InstantCharacter)\]\[[xDiT](https://github.com/xdit-project/xDiT)\]
      • [paper
      • [paper
      • [paper
      • [paper
      • [blog - forest-labs/flux)\]
      • [paper - MAI/Z-Image)\]
      • [blog - forest-labs/flux)\]\[[FLUX.2](https://github.com/black-forest-labs/flux2)\]

    • 5. Multimodal LLM

      • [paper
      • [paper - pytorch](https://github.com/lucidrains/flamingo-pytorch)\]
      • [paper - liu/LLaVA)\]\[[LLaVA-Pretrain Dataset](https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain)\]\[[ViP-LLaVA](https://github.com/WisconsinAIVision/ViP-LLaVA)\]\[[LLaVA-pp](https://github.com/mbzuai-oryx/LLaVA-pp)\]\[[TinyLLaVA_Factory](https://github.com/TinyLLaVA/TinyLLaVA_Factory)\]\[[LLaVA-RLHF](https://github.com/llava-rlhf/LLaVA-RLHF)\]\[[LLaVA-KD](https://github.com/Fantasyele/LLaVA-KD)\]
      • [paper - CAIR/MiniGPT-4)\]\[[MiniGPT-4-ZH](https://github.com/RiseInRose/MiniGPT-4-ZH)\]
      • [paper - liu/LLaVA/blob/main/docs/MODEL_ZOO.md)\]\[[LLaVA-UHD](https://github.com/thunlp/LLaVA-UHD)\]\[[LLaVA-HR](https://github.com/luogen1996/LLaVA-HR)\]
      • [paper - Med)\]
      • [paper
      • [paper - NLP-SG/Video-LLaMA)\]\[[VideoLLaMA2](https://github.com/DAMO-NLP-SG/VideoLLaMA2)\]\[[VideoLLaMA3](https://github.com/DAMO-NLP-SG/VideoLLaMA3)\]\[[VideoRefer](https://github.com/DAMO-NLP-SG/VideoRefer)\]\[[VideoLLM-online](https://github.com/showlab/VideoLLM-online)\]\[[LLaMA-VID](https://github.com/dvlab-research/LLaMA-VID)\]
      • [paper - research/bubogpt)\]\[[OFA](https://github.com/OFA-Sys/OFA)\]\[[AnyGPT](https://github.com/OpenMOSS/AnyGPT)\]
      • [paper - VL)\]
      • [paper - GPT/NExT-GPT)\]
      • [paper - InternVL](https://arxiv.org/abs/2410.08202)\]\[[InternVL2.5 paper](https://arxiv.org/abs/2412.05271)\]\[[InternVL3](https://arxiv.org/abs/2504.10479)\]\[[InternVL3.5](https://arxiv.org/abs/2508.18265)\]\[[InternVL-Data](https://www.modelscope.cn/datasets/OpenGVLab/InternVL-Data)\]
      • [paper - YuanGroup/MoE-LLaVA)\]\[[Visualization](https://github.com/PKU-YuanGroup/MoE-LLaVA/blob/main/docs/VISUALIZATION.md)\]
      • [paper - FVG/OpenDWM)\]\[[Matrix-Game](https://arxiv.org/abs/2506.18701)\]\[[Matrix-Game 2.0](https://arxiv.org/abs/2508.13009)\]
      • [paper - ferret)\]\[[Ferret-UI](https://arxiv.org/abs/2404.05719)\]\[[Ferret-UI 2](https://arxiv.org/abs/2410.18967)\]
      • [paper - Prompt](https://github.com/SunzeY/X-Prompt)\]
      • [paper - Benchmarks/Video-MME)\]\[[MME-RealWorld](https://github.com/MME-Benchmarks/MME-RealWorld)\]\[[lmms-eval](https://github.com/EvolvingLMMs-Lab/lmms-eval)\]\[[VLMEvalKit](https://github.com/open-compass/VLMEvalKit)\]\[[multimodal-needle-in-a-haystack](https://github.com/Wang-ML-Lab/multimodal-needle-in-a-haystack)\]\[[MM-NIAH](https://github.com/OpenGVLab/MM-NIAH)\]\[[VideoNIAH](https://github.com/joez17/VideoNIAH)\]\[[ChartMimic](https://github.com/ChartMimic/ChartMimic)\]\[[WildVision](https://arxiv.org/abs/2406.11069)\]\[[HourVideo](https://hourvideo.stanford.edu/)\]\[[MME-VideoOCR](https://github.com/DogNeverSleep/MME-VideoOCR)\]
      • [paper - 4m)\]\[[MM1.5](https://arxiv.org/abs/2409.20566)\]
      • [paper - mllm/cambrian)\]\[[LVLM_Interpretation](https://github.com/bytedance/LVLM_Interpretation)\]
      • [paper - Intelligence/openpi)\]\[[π0](https://arxiv.org/abs/2410.24164)\]\[[open-pi-zero](https://github.com/allenzren/open-pi-zero)\]\[[Emma-X](https://github.com/declare-lab/Emma-X)\]\[[RoboVLMs](https://github.com/Robot-VLAs/RoboVLMs)\]\[[RoboFlamingo](https://github.com/RoboFlamingo/RoboFlamingo)\]\[[SpatialVLA](https://github.com/SpatialVLA/SpatialVLA)\]\[[SpatialLM](https://manycore-research.github.io/SpatialLM/)\]\[[Hybrid-VLA](https://github.com/PKU-HMI-Lab/Hybrid-VLA)\]\[[OpenVLA-OFT](https://github.com/moojink/openvla-oft)\]\[[UniVLA](https://github.com/OpenDriveLab/UniVLA)\]\[[UniVLA BAAI](https://github.com/baaivision/UniVLA)\]\[[SimpleVLA-RL](https://github.com/PRIME-RL/SimpleVLA-RL)\]\[[SmolVLA](https://arxiv.org/abs/2506.01844)\]\[[WorldVLA](https://github.com/alibaba-damo-academy/WorldVLA)\]\[[villa-X](https://github.com/microsoft/villa-x)\]\[[VLAC](https://github.com/InternRobotics/VLAC)\]
      • [paper
      • [datacomp - 1T](https://github.com/mlfoundations/MINT-1T)\]\[[OpenVid-1M](https://github.com/NJU-PCALab/OpenVid-1M)\]\[[SkyScript-100M](https://github.com/vaew/SkyScript-100M)\]\[[FineVideo](https://github.com/huggingface/fineVideo)\]
      • [paper - VL)\]\[[modeling_qwen2_vl.py](https://github.com/huggingface/transformers/blob/main/src/transformers/models/qwen2_vl/modeling_qwen2_vl.py)\]\[[qwen2.5-vl blog](https://qwenlm.github.io/blog/qwen2.5-vl)\]\[[finetune-Qwen2-VL](https://github.com/zhangfaen/finetune-Qwen2-VL)\]\[[Qwen2-VL-Finetune](https://github.com/2U1/Qwen2-VL-Finetune)\]\[[Oryx](https://github.com/Oryx-mllm/Oryx)\]\[[Video-XL](https://github.com/VectorSpaceLab/Video-XL)\]\[[Video-ChatGPT](https://github.com/mbzuai-oryx/Video-ChatGPT)\]
      • [paper - tmg/umoe-scaling-unified-multimodal-llms)\]\[[Awesome-Large-Multimodal-Reasoning-Models](https://github.com/HITsz-TMG/Awesome-Large-Multimodal-Reasoning-Models)\]
      • [paper
      • [paper - VL/LLaVA-NeXT/tree/main/scripts/train)\]\[[FastVLM](https://github.com/apple/ml-fastvlm)\]\[[LLaVA-OneVision-1.5](https://github.com/EvolvingLMMs-Lab/LLaVA-OneVision-1.5)\]
      • [mllm - finetune](https://github.com/zjysteven/lmms-finetune)\]
      • [paper - YuanGroup/Video-LLaVA)\]\[[PLLaVA](https://github.com/magic-research/PLLaVA)\]\[[ml-slowfast-llava](https://github.com/apple/ml-slowfast-llava)\]
      • [paper - ai-lab/MiniGPT-5)\]
      • [paper - 6B](https://github.com/THUDM/VisualGLM-6B)\]\[[CogCoM](https://github.com/THUDM/CogCoM)\]
      • [paper - VL/LLaVA-NeXT)\]\[[LLaVA-Plus-Codebase](https://github.com/LLaVA-VL/LLaVA-Plus-Codebase)\]\[[Open-LLaVA-NeXT](https://github.com/xiaoachen98/Open-LLaVA-NeXT)\]\[[MG-LLaVA](https://github.com/PhoenixZ810/MG-LLaVA)\]\[[LongVA](https://github.com/EvolvingLMMs-Lab/LongVA)\]\[[LongLLaVA](https://github.com/FreedomIntelligence/LongLLaVA)\]\[[LLaVA-Mini](https://github.com/ictnlp/LLaVA-Mini)\]
      • [paper - CAIR/MiniGPT-4)\]
      • [paper - anything)\]
      • [paper - ai/Janus)\]\[[JanusFlow](https://arxiv.org/abs/2411.07975)\]
      • [paper
      • [paper - o)\]\[[Show-o2](https://arxiv.org/abs/2506.15564)\]\[[D-AR](https://arxiv.org/abs/2505.23660)\]\[[UniRL](https://arxiv.org/abs/2505.23380)\]\[[Show-o-Turbo](https://github.com/zhijie-group/Show-o-Turbo)\]\[[OmniGen](https://github.com/VectorSpaceLab/OmniGen)\]\[[Transfusion](https://arxiv.org/abs/2408.11039)\]\[[VILA-U](https://arxiv.org/abs/2409.04429)\]\[[LWM](https://github.com/LargeWorldModel/LWM)\]\[[VARGPT](https://github.com/VARGPT-family/VARGPT-v1.1)\]\[[HermesFlow](https://github.com/Gen-Verse/HermesFlow)\]\[[SAIL](https://arxiv.org/abs/2504.10462)\]
      • [paper - NLP/anole)\]\[[Orthus](https://github.com/zhijie-group/Orthus)\]
      • [paper
      • [paper
      • [paper - CAIR/LongVU)\]\[[Video-XL](https://github.com/VectorSpaceLab/Video-XL)\]\[[VisionZip](https://github.com/dvlab-research/VisionZip)\]\[[Apollo](https://arxiv.org/abs/2412.10360)\]
      • [paper - VL/LLaVA-NeXT/blob/main/docs/LLaVA_Video_1003.md)\]\[[LLaVA-Critic](https://arxiv.org/abs/2410.02712)\]\[[LLaVA-Critic-R1](https://arxiv.org/abs/2509.00676)\]\[[LLaVA-Video-178K](https://huggingface.co/datasets/lmms-lab/LLaVA-Video-178K)\]\[[VLog](https://github.com/showlab/VLog)\]
      • [paper - omni/mini-omni2)\]\[[moshivis](https://github.com/kyutai-labs/moshivis)\]\[[Stream-Omni](https://github.com/ictnlp/Stream-Omni)\]
      • [paper
      • [paper - SALMONN-2](https://github.com/bytedance/video-SALMONN-2)\]
      • [paper - CAIR/MiniGPT4-video)\]
      • [paper
      • [paper - ai/DeepSeek-VL)\]
      • [paper - HaoranWei/Vary-toy)\]\[[Slow-Perception](https://github.com/Ucas-HaoranWei/Slow-Perception)\]
      • [paper - HaoranWei/Vary)\]
      • [paper - ai/DeepSeek-VL2)\]
      • [paper - Tokenizer](https://github.com/NVIDIA/Cosmos-Tokenizer)\]\[[Genesis](https://github.com/Genesis-Embodied-AI/Genesis)\]\[[mujoco_menagerie](https://github.com/google-deepmind/mujoco_menagerie)\]\[[Aether](https://github.com/InternRobotics/Aether)\]
      • [paper - V](https://github.com/RLHF-V/RLHF-V)\]\[[RLAIF-V](https://github.com/RLHF-V/RLAIF-V)\]\[[MM-RLHF](https://github.com/Kwai-YuanQi/MM-RLHF)\]\[[OmniAlign-V](https://github.com/PhoenixZ810/OmniAlign-V)\]\[[VisRL](https://github.com/zhangquanchen/VisRL)\]\[[Reason-RFT](https://github.com/tanhuajie/Reason-RFT)\]\[[MM-UPT](https://github.com/waltonfuture/MM-UPT)\]\[[GRPO-CARE](https://github.com/TencentARC/GRPO-CARE)\]\[[X-Omni](https://github.com/X-Omni-Team/X-Omni)\]
      • [paper
      • [paper - RFT)\]\[[Visual-ARFT](https://arxiv.org/abs/2505.14246)\]\[[UnifiedReward](https://github.com/CodeGoat24/UnifiedReward)\]\[[R1-Reward](https://arxiv.org/abs/2505.02835)\]\[[Skywork-VL Reward](https://arxiv.org/abs/2505.07263)\]\[[V-Triune](https://arxiv.org/abs/2505.18129)\]
      • [paper - Omni)\]\[[OmniTalker](https://arxiv.org/abs/2504.02433)\]\[[Qwen VLo](https://qwenlm.github.io/blog/qwen-vlo/)\]
      • [paper
      • [paper - Seed/Seed1.5-VL)\]\[[VeOmni](https://github.com/ByteDance-Seed/VeOmni)\]\[[Kimi-VL](https://arxiv.org/abs/2504.07491)\]\[[MiMo-VL](https://arxiv.org/abs/2506.03569)\]\[[Kwai Keye-VL](https://github.com/Kwai-Keye/Keye)\]
      • [paper - MLLM/VITA)\]\[[Tencent/VITA](https://github.com/Tencent/VITA)\]\[[VITA-1.5](https://arxiv.org/abs/2501.01957)\]\[[Freeze-Omni](https://github.com/VITA-MLLM/Freeze-Omni)\]\[[Long-VITA](https://github.com/VITA-MLLM/Long-VITA)\]\[[VITA-Audio](https://github.com/VITA-MLLM/VITA-Audio)\]\[[Lyra](https://github.com/dvlab-research/Lyra)\]\[[Ola](https://github.com/Ola-Omni/Ola)\]
      • [paper - ai/Janus)\]
      • [paper - seed/BAGEL)\]\[[Hyper-Bagel](https://arxiv.org/abs/2509.18824)\]\[[UniWorld](https://github.com/PKU-YuanGroup/UniWorld)\]\[[TransDiff](https://github.com/TransDiff/TransDiff)\]\[[GPT-Image-Edit](https://github.com/wyhlovecpp/GPT-Image-Edit)\]\[[RecA](https://github.com/HorizonWind2004/reconstruction-alignment)\]\[[LaViDa-O](https://github.com/jacklishufan/LaViDa-O)\]
      • [paper - Vet)\]\[[UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling](https://arxiv.org/abs/2408.04810)\]\[[Thinking in Space](https://arxiv.org/abs/2412.14171)\]
      • [paper - 4v-9b](https://huggingface.co/THUDM/glm-4v-9b/blob/main/modeling_chatglm.py)\]
      • [paper - V)\]
      • [paper - V)\]\[[blog](https://openbmb.notion.site/823e063f3dec4b82a00790890e20378b?v=691da33ab71a436799484ecfd00005a9)\]\[[MiniCPM-V 4.5](https://arxiv.org/abs/2509.18154)\]\[[VisCPM](https://github.com/OpenBMB/VisCPM)\]\[[RLHF-V](https://github.com/RLHF-V/RLHF-V)\]\[[RLAIF-V](https://github.com/RLHF-V/RLAIF-V)\]\[[BlueLM-2.5-3B Technical Report](https://arxiv.org/abs/2507.05934)\]
      • [paper - Flash-Omni](https://arxiv.org/abs/2510.24821)\]\[[M2-omni](https://arxiv.org/abs/2502.18778)\]\[[Ming-Lite-Uni](https://arxiv.org/abs/2505.02471)\]\[[Ming-UniVision](https://arxiv.org/abs/2510.06590)\]\[[ViLaSR](https://github.com/AntResearchNLP/ViLaSR)\]
      • [paper - org/GLM-V)\]
      • [paper - XComposer)\]\[[InternLM-XComposer2.5-OmniLive](https://arxiv.org/abs/2412.09596)\]\[[InternLM-XComposer2.5-Reward](https://arxiv.org/abs/2501.12368)\]
      • [paper - Liu/Monkey)\]
      • [paper - 4o-Image](https://github.com/FreedomIntelligence/ShareGPT-4o-Image)\]
      • [paper
      • [paper - Hunyuan/HunyuanWorld-1.0)\]\[[HunyuanWorld-Voyager](https://github.com/Tencent-Hunyuan/HunyuanWorld-Voyager)\]\[[HunyuanWorld-Mirror](https://github.com/Tencent-Hunyuan/HunyuanWorld-Mirror)\]\[[FlashWorld](https://github.com/imlixinyang/FlashWorld)\]
      • [MiniCPM-V - AutoML/MobileVLM)\]\[[OmniFusion](https://github.com/AIRI-Institute/OmniFusion)\]\[[Bunny](https://github.com/BAAI-DCAI/Bunny)\]\[[MiCo](https://github.com/invictus717/MiCo)\]\[[Vitron](https://github.com/SkyworkAI/Vitron)\]\[[mPLUG-Owl](https://github.com/X-PLUG/mPLUG-Owl)\]\[[mPLUG-DocOwl](https://github.com/X-PLUG/mPLUG-DocOwl)\]\[[Ovis](https://github.com/AIDC-AI/Ovis)\]\[[Ovis-U1](https://github.com/AIDC-AI/Ovis-U1)\]\[[Aria](https://github.com/rhymes-ai/Aria)\]\[[unicom](https://github.com/deepglint/unicom)\]\[[Infini-Megrez](https://github.com/infinigence/Infini-Megrez)\]
      • [paper - Omni)\]\[[LongCat-Flash-Omni Technical Report](https://arxiv.org/abs/2511.00279)\]\[[OmniVinci](https://github.com/NVlabs/OmniVinci)\]
      • [paper - VL)\]\[[modeling_qwen2_5_vl.py](https://github.com/huggingface/transformers/blob/main/src/transformers/models/qwen2_5_vl/modeling_qwen2_5_vl.py)\]
      • [paper
      • [paper - Reader](https://github.com/Tencent/POINTS-Reader)\]\[[Multi-Modal Generative Embedding Model](https://arxiv.org/abs/2405.19333)\]\[[Number it: Temporal Grounding Videos like Flipping Manga](https://arxiv.org/abs/2411.10332)\]\[[Valley](https://github.com/bytedance/Valley)\]\[[RDTF](https://arxiv.org/abs/2503.17735)\]\[[KuaiMod](https://arxiv.org/abs/2504.14904)\]
      • [paper - research/big_vision/tree/main/big_vision/configs/proj/paligemma)\]\[[pytorch-paligemma](https://github.com/hkproj/pytorch-paligemma)\]\[[PaliGemma 2](https://arxiv.org/abs/2412.03555)\]
      • [paper - 12b/)\]\[[Pixtral-12B-2409](https://huggingface.co/mistralai/Pixtral-12B-2409)\]\[[Pixtral-Large-Instruct-2411](https://huggingface.co/mistralai/Pixtral-Large-Instruct-2411)\]\[[Mistral Small 3.1](https://mistral.ai/news/mistral-small-3-1)\]
      • [paper
      • [paper
      • [paper - world)\]\[[LingBot-VA](https://github.com/Robbyant/lingbot-va)\]\[[Reasoning-Visual-World](https://github.com/thuml/Reasoning-Visual-World)\]
      • [nature paper

    • 4. Diffusion Model

      • [paper - diffusion)\]\[[CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion)\]\[[Stability-AI/stablediffusion](https://github.com/Stability-AI/stablediffusion)\]\[[ml-stable-diffusion](https://github.com/apple/ml-stable-diffusion)\]\[[cleandift](https://github.com/CompVis/cleandift)\]
      • [paper - Video-Diffusion-Models)\]
      • [paper
      • [paper - Models-Papers-Survey-Taxonomy)\]
      • [paper - pytorch](https://github.com/lucidrains/magvit2-pytorch)\]\[[Open-MAGVIT2](https://github.com/TencentARC/Open-MAGVIT2)\]\[[LlamaGen](https://github.com/FoundationVision/LlamaGen)\]
      • [paper - consistency-model)\]\[[Hyper-SD](https://huggingface.co/ByteDance/Hyper-SD)\]\[[DMD2](https://github.com/tianweiy/DMD2)\]\[[ddim](https://github.com/ermongroup/ddim)\]
      • [paper - text2im)\]
      • [paper - AI/generative-models)\]\[[SDXL-Lightning](https://huggingface.co/ByteDance/SDXL-Lightning)\]
      • [paper
      • [paper - diffusion-pytorch)\]
      • [paper - HPC-AI-Lab/VideoSys)\]\[[MDT](https://github.com/sail-sg/MDT)\]\[[fast-DiT](https://github.com/chuanyangjin/fast-DiT)\]\[[FastVideo](https://github.com/hao-ai-lab/FastVideo)\]\[[xDiT](https://github.com/xdit-project/xDiT)\]\[[PipeFusion](https://github.com/PipeFusion/PipeFusion)\]\[[rlt](https://github.com/rccchoudhury/rlt)\]\[[U-DiT](https://github.com/YuchuanTian/U-DiT)\]\[[LightningDiT](https://github.com/hustvl/LightningDiT)\]\[[RAE](https://github.com/bytetriper/RAE)\]\[[SVG](https://github.com/shiml20/SVG)\]
      • [paper - ViT)\]\[[RIFLEx](https://github.com/thu-ml/RIFLEx)\]
      • [paper - free-guidance-pytorch)\]
      • [paper - diffusion)\]
      • [paper - diffusion)\]
      • [paper - diffusion-pytorch)\]\[[RDDM](https://github.com/nachifur/RDDM)\]
      • [paper - mdm)\]
      • [paper - ml/unidiffuser)\]
      • [paper - Entropy-Discrete-Diffusion)\]
      • [paper - AI/generative-models)\]
      • [paper - AI/generative-models)\]\[[Stable Video 4D](https://huggingface.co/stabilityai/sv4d)\]\[[VideoCrafter](https://github.com/AILab-CVC/VideoCrafter)\]\[[Video-Infinity](https://github.com/Yuanshi9815/Video-Infinity)\]
      • [paper
      • [link - AI/StableCascade)\]\[[model](https://huggingface.co/stabilityai/stable-cascade)\]
      • [paper - NJU/DDT)\]\[[REPA-E](https://arxiv.org/abs/2504.10483)\]
      • [paper
      • [paper - diffusion-3-medium)\]\[[mmdit](https://github.com/lucidrains/mmdit)\]
      • [paper - SD)\]\[[AdaCache](https://github.com/AdaCache-DiT/AdaCache)\]
      • [Fooocus
      • [stable-diffusion-webui - diffusion-webui-colab](https://github.com/camenduru/stable-diffusion-webui-colab)\]\[[sd-webui-controlnet](https://github.com/Mikubill/sd-webui-controlnet)\]\[[stable-diffusion-webui-forge](https://github.com/lllyasviel/stable-diffusion-webui-forge)\]\[[automatic](https://github.com/vladmandic/automatic)\]
      • [Awesome-Diffusion-Models - Video-Diffusion](https://github.com/showlab/Awesome-Video-Diffusion)\]
      • [ComfyUI - app/gradio)\]\[[ComfyUI-Workflows-ZHO](https://github.com/ZHO-ZHO-ZHO/ComfyUI-Workflows-ZHO)\]\[[ComfyUI_Bxb](https://github.com/zhulu111/ComfyUI_Bxb)\]\[[ComfyUI-Manager](https://github.com/Comfy-Org/ComfyUI-Manager)\]\[[ComfyUI-Copilot](https://github.com/AIDC-AI/ComfyUI-Copilot)\]
      • [diffusers - Studio](https://github.com/modelscope/DiffSynth-Studio)\]\[[diffusion-pipe](https://github.com/tdrussell/diffusion-pipe)\]
      • [paper - consistency-model)\]\[[diffusion-forcing](https://github.com/buoyancy99/diffusion-forcing)\]\[[InstaFlow](https://github.com/gnobitab/InstaFlow)\]
      • [paper - vilab/In-Context-LoRA)\]
      • [paper - forcing)\]
      • [paper - stable-diffusion-3-5)\]
      • [paper - stabilizing-and-scaling-continuous-time-consistency-models/)\]\[[rCM](https://github.com/NVlabs/rcm)\]
      • [paper - han-lab/nunchaku)\]\[[SnapGen](https://arxiv.org/abs/2412.09619)\]
      • [paper - pytorch](https://github.com/lucidrains/transfusion-pytorch)\]\[[chameleon](https://github.com/facebookresearch/chameleon)\]\[[MonoFormer](https://github.com/MonoFormer/MonoFormer)\]\[[MetaMorph](https://arxiv.org/abs/2412.14164)\]\[[LMFusion](https://arxiv.org/abs/2412.15188)\]\[[MetaQueries](https://github.com/facebookresearch/metaquery)\]\[[OpenUni](https://github.com/wusize/OpenUni)\]\[[Token-Shuffle](https://arxiv.org/abs/2504.17789)\]
      • [paper - research/Regional-Prompting-FLUX)\]\[[Add-it](https://research.nvidia.com/labs/par/addit)\]\[[RAG-Diffusion](https://github.com/NJU-PCALab/RAG-Diffusion)\]\[[DiTCtrl](https://github.com/TencentARC/DiTCtrl)\]
      • [paper - models-class](https://github.com/huggingface/diffusion-models-class)\]\[[The Principles of Diffusion Models](https://arxiv.org/abs/2510.21890)\]
      • [paper - autumn/StreamDiffusion)\]
      • [paper - DiT)\]
      • [paper - stable-diffusion](https://github.com/ThisisBillhe/tiny-stable-diffusion)\]
      • [paper
      • [paper - yu/REPA)\]\[[VideoREPA](https://github.com/aHapBean/VideoREPA)\]
      • [paper - Generation-CoT](https://github.com/ZiyuGuo99/Image-Generation-CoT)\]\[[Reflect-DiT](https://github.com/jacklishufan/Reflect-DiT)\]\[[T2I-R1](https://github.com/CaraJ7/T2I-R1)\]\[[Video-T1](https://github.com/liuff19/Video-T1)\]\[[ttt-video-dit](https://arxiv.org/abs/2504.05298)\]\[[SRPO](https://github.com/Tencent-Hunyuan/SRPO)\]
      • [paper
      • [paper - ml/TurboDiffusion)\]\[[fast-DiT](https://github.com/chuanyangjin/fast-DiT)\]\[[FastVideo](https://github.com/hao-ai-lab/FastVideo)\]\[[xDiT](https://github.com/xdit-project/xDiT)\]

    • 8. Survey for Multimodal

      • [paper - LLMs-for-Video-Understanding)\]
      • [paper - vision-in-the-wild/cvinw_readings)\]
      • [paper - Multimodal-Large-Language-Models](https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models)\]\[[Aligning Multimodal LLM with Human Preference: A Survey](https://arxiv.org/abs/2503.14504)\]\[[MME](https://arxiv.org/abs/2306.13394)\]\[[MME-Survey](https://arxiv.org/abs/2411.15296)\]
      • [paper
      • [paper - Multimodal-LLMs-Survey)\]
      • [paper
      • [paper
      • [paper - Multimodal-Next-Token-Prediction)\]\[[Unified Multimodal Understanding and Generation Models](https://arxiv.org/abs/2505.02567)\]
      • [paper

    • 7. Text2Video

      • [paper
      • [paper - Lightning](https://huggingface.co/ByteDance/AnimateDiff-Lightning)\]
      • [paper - Your-Pose v2](https://arxiv.org/abs/2406.03035)\]\[[Follow-Your-Emoji](https://arxiv.org/abs/2406.01900)\]
      • [paper - AI-Research/Text2Video-Zero)\]\[[StreamingT2V](https://github.com/Picsart-AI-Research/StreamingT2V)\]\[[ControlVideo](https://github.com/YBYBZhang/ControlVideo)\]
      • [paper - A-Video)\]
      • [paper - a-video-pytorch](https://github.com/lucidrains/make-a-video-pytorch)\]\[[Make-An-Audio-2](https://github.com/bytedance/Make-An-Audio-2)\]
      • [paper
      • [paper
      • [paper
      • [paper - AnimateAnyone](https://github.com/guoqincode/Open-AnimateAnyone)\]\[[Moore-AnimateAnyone](https://github.com/MooreThreads/Moore-AnimateAnyone)\]\[[AnimateAnyone](https://github.com/novitalabs/AnimateAnyone)\]\[[UniAnimate](https://github.com/ali-vilab/UniAnimate)\]\[[Animate-X](https://arxiv.org/abs/2410.10306)\]\[[StableAnimator](https://github.com/Francis-Rings/StableAnimator)\]\[[DisPose](https://github.com/lihxxx/DisPose)\]\[[OmniAvatar](https://github.com/Omni-Avatar/OmniAvatar)\]
      • [paper - research/magic-animate)\]\[[champ](https://github.com/fudan-generative-vision/champ)\]\[[MegActor](https://github.com/megvii-research/MegActor)\]\[[X-Dyna](https://github.com/bytedance/X-Dyna)\]
      • [paper - vilab/VGen)\]
      • [paper - project)\]\[[HuMo](https://github.com/Phantom-video/HuMo)\]\[[MOSAIC](https://github.com/bytedance-fanqie-ai/MOSAIC)\]
      • [paper - vilab/VGen)\]
      • [paper - LiangF/FlowVid)\]
      • [paper - 2.0](https://github.com/Vchitect/Vchitect-2.0)\]\[[LiteGen](https://github.com/Vchitect/LiteGen)\]
      • [paper
      • [paper - pytorch](https://github.com/lucidrains/lumiere-pytorch)\]
      • [paper - animation](https://github.com/snap-research/articulated-animation)\]
      • [paper - Express](https://github.com/tencent-ailab/V-Express)\]\[[EMO2](https://arxiv.org/abs/2501.10687)\]
      • [paper - sun/SoraReview)\]
      • [paper - sun/Mora)\]
      • [paper - Yang/AniPortrait)\]
      • [paper
      • [MoneyPrinterTurbo - hf/clapper)\]\[[videos](https://github.com/3b1b/videos)\]\[[manim](https://github.com/3b1b/manim)\]\[[ManimML](https://github.com/helblazer811/ManimML)\]\[[Manim MCP Server](https://github.com/abhiemj/manim-mcp-server)\]\[[TheoremExplainAgent](https://github.com/TIGER-AI-Lab/TheoremExplainAgent)\]\[[Mochi 1](https://github.com/genmoai/mochi)\]\[[genmoai-smol](https://github.com/victorchall/genmoai-smol)\]\[[Kandinsky-4](https://github.com/ai-forever/Kandinsky-4)\]\[[story-flicks](https://github.com/alecm20/story-flicks)\]\[[Cosmos](https://github.com/NVIDIA/Cosmos)\]\[[Code2Video](https://github.com/showlab/Code2Video)\]
      • [Awesome-Video-Diffusion - Controllable-Video-Generation](https://github.com/mayuelala/Awesome-Controllable-Video-Generation)\]
      • [paper - r-r-o-w/finetrainers)\]\[[VideoTuna](https://github.com/VideoVerses/VideoTuna)\]\[[TransPixar](https://github.com/wileewang/TransPixar)\]\[[STAR](https://github.com/NJU-PCALab/STAR)\]\[[FlashVideo](https://github.com/FoundationVision/FlashVideo)\]\[[VideoX-Fun](https://github.com/aigc-apps/VideoX-Fun)\]\[[TesserAct](https://github.com/UMass-Embodied-AGI/TesserAct)\]
      • [paper - T2X](https://github.com/360CVGroup/Qihoo-T2X)\]
      • [paper
      • [paper - Flow)\]\[[LaVIT](https://github.com/jy0205/LaVIT)\]\[[ml-tarflow](https://github.com/apple/ml-tarflow)\]
      • [paper
      • [paper - Hunyuan/HunyuanVideo)\]\[[HunyuanVideo-I2V](https://github.com/Tencent/HunyuanVideo-I2V)\]\[[HunyuanCustom](https://github.com/Tencent/HunyuanCustom)\]\[[HunyuanVideo-Avatar](https://github.com/Tencent-Hunyuan/HunyuanVideo-Avatar)\]\[[HunyuanPortrait](https://github.com/Tencent-Hunyuan/HunyuanPortrait)\]\[[DreamO](https://github.com/bytedance/DreamO)\]\[[FastVideo](https://github.com/hao-ai-lab/FastVideo)\]\[[Sparse-VideoGen](https://github.com/svg-project/Sparse-VideoGen)\]\[[HunyuanVideoGP](https://github.com/deepbeepmeep/HunyuanVideoGP)\]
      • [paper - 1](https://github.com/SandAI-org/MAGI-1)\]\[[Self Forcing](https://github.com/guandeh17/Self-Forcing)\]\[[Self-Forcing++](https://github.com/justincui03/Self-Forcing-Plus-Plus)\]\[[PAR](https://github.com/yuqingwang1029/PAR)\]\[[Lumos-1](https://github.com/alibaba-damo-academy/Lumos)\]
      • [paper - ai/Step-Video-T2V)\]\[[Step-Video-TI2V](https://github.com/stepfun-ai/Step-Video-TI2V)\]\[[OmniSVG](https://github.com/OmniSVG/OmniSVG)\]
      • [paper - Sora)\]\[[Open-Sora 2.0](https://arxiv.org/abs/2503.09642)\]\[[VideoSys](https://github.com/NUS-HPC-AI-Lab/VideoSys)\]
      • [paper - V1](https://github.com/SkyworkAI/SkyReels-V1)\]\[[SkyReels-V2](https://github.com/SkyworkAI/SkyReels-V2)\]\[[SkyReels-A1](https://github.com/SkyworkAI/SkyReels-A1)\]\[[SkyReels-A2](https://github.com/SkyworkAI/SkyReels-A2)\]
      • [paper - Video/Wan2.1)\]\[[Wan2.2](https://github.com/Wan-Video/Wan2.2)\]\[[Wan-S2V](https://arxiv.org/abs/2508.18621)\]\[[VACE](https://github.com/ali-vilab/VACE)\]\[[Index-AniSora](https://github.com/bilibili/Index-anisora)\]\[[Long-RL](https://github.com/NVlabs/Long-RL)\]\[[LongLive](https://github.com/NVlabs/LongLive)\]\[[LongCat-Video](https://github.com/meituan-longcat/LongCat-Video)\]
      • [paper - project/xDiT)\]
      • [paper - Seed/SeedVR)\]
      • [paper
      • [paper - Video)\]\[[LTX-Video-Trainer](https://github.com/Lightricks/LTX-Video-Trainer)\]
      • [paper
      • [blog - 2023-100.pdf)\]\[[Generative Models of Images and Neural Networks](https://www2.eecs.berkeley.edu/Pubs/TechRpts/2023/EECS-2023-108.pdf)\]\[[Open-Sora](https://github.com/hpcaitech/Open-Sora)\]\[[VideoSys](https://github.com/NUS-HPC-AI-Lab/VideoSys)\]\[[Open-Sora-Plan](https://github.com/PKU-YuanGroup/Open-Sora-Plan)\]\[[minisora](https://github.com/mini-sora/minisora)\]\[[SoraWebui](https://github.com/SoraWebui/SoraWebui)\]\[[MuseV](https://github.com/TMElyralab/MuseV)\]\[[PhysDreamer](https://github.com/a1600012888/PhysDreamer)\]\[[easyanimate](https://github.com/aigc-apps/easyanimate)\]
      • [paper
      • [paper - World/goku)\]\[[Seaweed-7B](https://arxiv.org/abs/2504.08685)\]\[[ATI](https://github.com/bytedance/ATI)\]
      • [paper - ai/Allegro)\]
      • [paper - YuanGroup/Open-Sora-Plan)\]\[[MagicTime](https://github.com/PKU-YuanGroup/MagicTime)\]\[[ConsisID](https://github.com/PKU-YuanGroup/ConsisID)\]\[[CoDeF](https://github.com/ant-research/CoDeF)\]\[[OmniConsistency](https://github.com/showlab/OmniConsistency)\]
      • [blog - gen)\]\[[VideoJAM](https://arxiv.org/abs/2502.02492)\]\[[MoCha](https://arxiv.org/abs/2503.23307)\]

    • 3. Clip

      • [paper - as-service](https://github.com/jina-ai/clip-as-service)\]\[[SigLIP](https://arxiv.org/abs/2303.15343)\]\[[EVA](https://github.com/baaivision/EVA)\]\[[DIVA](https://github.com/baaivision/DIVA)\]\[[Clip-Forge](https://github.com/AutodeskAILab/Clip-Forge)\]\[[CLIP Benchmark](https://github.com/LAION-AI/CLIP_benchmark)\]
      • [paper - Free Visual Representation Learning](https://arxiv.org/abs/2504.01017)\]
      • [paper
      • [paper - Sys/Chinese-CLIP)\]
      • [paper - pytorch)\]
      • [paper
      • [paper
      • [paper - CLIP)\]\[[EVA-CLIP-18B](https://arxiv.org/abs/2402.04252)\]\[[FG-CLIP](https://github.com/360CVGroup/FG-CLIP)\]\[[TokLIP](https://github.com/TencentARC/TokLIP)\]\[[RWKV-CLIP](https://github.com/deepglint/RWKV-CLIP)\]
      • [paper
      • [paper
      • [paper - Training to 4K Resolution](https://nvlabs.github.io/PS3/)\]\[[PS3](https://github.com/NVlabs/PS3)\]
      • [paper - mobileclip)\]\[[MobileCLIP2](https://arxiv.org/abs/2508.20691)\]\[[FastVLM](https://github.com/apple/ml-fastvlm)\]
      • [paper - CLIP)\]\[[Inf-CLIP](https://github.com/DAMO-NLP-SG/Inf-CLIP)\]
      • [paper
      • [paper - cls/superclass)\]
      • [paper - aim)\]
      • [paper - VLAA/OpenVision)\]\[[OpenVision 2](https://arxiv.org/abs/2509.01644)\]\[[Recap-DataComp-1B](https://github.com/UCSC-VLAA/Recap-DataComp-1B)\]\[[CLIPS](https://github.com/UCSC-VLAA/CLIPS)\]

    • 2. Blip

    • 9. Other

      • [paper - Lab/Otter)\]
      • [blog - 8b)\]
      • [paper - VLLM/Lumina-T2X)\]\[[Lumina-Image-2.0](https://github.com/Alpha-VLLM/Lumina-Image-2.0)\]\[[Lumina-DiMOO](https://github.com/Alpha-VLLM/Lumina-DiMOO)\]
      • [paper - CVC/SEED-X)\]\[[SEED](https://github.com/AILab-CVC/SEED)\]\[[SEED-Story](https://github.com/TencentARC/SEED-Story)\]\[[SEED-Bench-R1](https://github.com/TencentARC/SEED-Bench-R1)\]\[[AnimeGamer](https://github.com/TencentARC/AnimeGamer)\]
      • [paper - Interleaved)\]
      • [paper
      • [paper
      • [paper - VLLM/LLaMA2-Accessory)\]
      • [paper - Lab/Otter)\]\[[model](https://huggingface.co/Otter-AI/OtterHD-8B)\]
      • [paper - VLLM/Lumina-mGPT)\]\[[Lumina-Video](https://github.com/Alpha-VLLM/Lumina-Video)\]\[[Lumina-mGPT 2.0](https://arxiv.org/abs/2507.17801)\]

    • 1. Audio

      • [paper - 82M](https://huggingface.co/hexgrad/Kokoro-82M)\]\[[kokoro-onnx](https://github.com/thewh1teagle/kokoro-onnx)\]
      • [paper - whisper](https://github.com/SYSTRAN/faster-whisper)\]\[[WhisperFusion](https://github.com/collabora/WhisperFusion)\]\[[whisper-diarization](https://github.com/MahmoudAshraf97/whisper-diarization)\]\[[OLMoASR](https://github.com/allenai/OLMoASR)\]
      • [paper - CTC](https://arxiv.org/abs/2410.05101)\]
      • [paper
      • [paper - whisper)\]
      • [paper - generative-vision/hallo)\]\[[hallo2](https://github.com/fudan-generative-vision/hallo2)\]\[[hallo3](https://github.com/fudan-generative-vision/hallo3)\]\[[champ](https://github.com/fudan-generative-vision/champ)\]\[[PersonaTalk](https://arxiv.org/abs/2409.05379)\]\[[JoyVASA](https://github.com/jdh-algo/JoyVASA)\]\[[memo](https://github.com/memoavatar/memo)\]\[[EDTalk](https://github.com/tanshuai0219/EDTalk)\]\[[LatentSync](https://github.com/bytedance/LatentSync)\]
      • [coqui-ai/TTS - ai/bark](https://github.com/suno-ai/bark)\]\[[ChatTTS](https://github.com/2noise/ChatTTS)\]\[[fish-speech](https://github.com/fishaudio/fish-speech)\]\[[CSM](https://github.com/SesameAILabs/csm)\]\[[WhisperSpeech](https://github.com/collabora/WhisperSpeech)\]\[[MeloTTS](https://github.com/myshell-ai/MeloTTS)\]\[[parler-tts](https://github.com/huggingface/parler-tts)\]\[[MARS5-TTS](https://github.com/Camb-ai/MARS5-TTS)\]\[[metavoice-src](https://github.com/metavoiceio/metavoice-src)\]\[[OuteTTS](https://github.com/edwko/OuteTTS)\]\[[RealtimeTTS](https://github.com/KoljaB/RealtimeTTS)\]\[[RealtimeSTT](https://github.com/KoljaB/RealtimeSTT)\]\[[RealtimeVoiceChat](https://github.com/KoljaB/RealtimeVoiceChat)\]\[[Zonos](https://github.com/Zyphra/Zonos)\]\[[Orpheus-TTS](https://github.com/canopyai/Orpheus-TTS)\]\[[MegaTTS3](https://github.com/bytedance/MegaTTS3)\]\[[index-tts](https://github.com/index-tts/index-tts)\]\[[dia](https://github.com/nari-labs/dia)\]\[[Chatterbox TTS](https://github.com/resemble-ai/chatterbox)\]\[[KittenTTS](https://github.com/KittenML/KittenTTS)\]
      • [FunASR - damo-academy/FunClip)\]\[[FunAudioLLM](https://github.com/FunAudioLLM)\]\[[wenet](https://github.com/wenet-e2e/wenet)\]\[[TeleSpeech-ASR](https://github.com/Tele-AI/TeleSpeech-ASR)\]\[[EmotiVoice](https://github.com/netease-youdao/EmotiVoice)\]\[[nanospeech](https://github.com/lucasnewman/nanospeech)\]\[[R1-AQA](https://github.com/xiaomi-research/r1-aqa)\]\[[PlayDiffusion](https://github.com/playht/PlayDiffusion)\]
      • [Retrieval-based-Voice-Conversion-WebUI - ChatTTS](https://github.com/panyanyany/Awesome-ChatTTS)\]\[[VoiceHub](https://github.com/kadirnar/VoiceHub)\]
      • [SadTalker - retalking](https://github.com/OpenTalker/video-retalking)\]\[[SadTalker-Video-Lip-Sync](https://github.com/Zz-ww/SadTalker-Video-Lip-Sync)\]\[[LatentSync](https://github.com/bytedance/LatentSync)\]\[[AniPortrait](https://github.com/Zejun-Yang/AniPortrait)\]\[[GeneFacePlusPlus](https://github.com/yerfor/GeneFacePlusPlus)\]\[[V-Express](https://github.com/tencent-ailab/V-Express)\]\[[MuseTalk](https://github.com/TMElyralab/MuseTalk)\]\[[EchoMimic](https://github.com/antgroup/echomimic)\]\[[echomimic_v2](https://github.com/antgroup/echomimic_v2)\]\[[MimicTalk](https://github.com/yerfor/MimicTalk)\]\[[Real3DPortrait](https://github.com/yerfor/Real3DPortrait)\]\[[MiniMates](https://github.com/kleinlee/MiniMates)\]\[[Linly-Talker](https://github.com/Kedreamix/Linly-Talker)\]\[[MultiTalk](https://github.com/MeiGen-AI/MultiTalk)\]\[[InfiniteTalk](https://github.com/MeiGen-AI/InfiniteTalk)\]
      • [stable-audio-tools - Audio](https://github.com/QwenLM/Qwen-Audio)\]\[[pyannote-audio](https://github.com/pyannote/pyannote-audio)\]\[[ims-toucan](https://github.com/digitalphonetics/ims-toucan)\]\[[AudioLCM](https://github.com/Text-to-Audio/AudioLCM)\]\[[speech-to-speech](https://github.com/eustlb/speech-to-speech)\]\[[ichigo](https://github.com/homebrewltd/ichigo)\]\[[TEN-Agent](https://github.com/TEN-framework/TEN-Agent)\]
      • [paper - omni/mini-omni)\]\[[mini-omni2](https://github.com/gpt-omni/mini-omni2)\]\[[Mini-Omni-Reasoner](https://github.com/xzf-thu/Mini-Omni-Reasoner)\]\[[moshi](https://github.com/kyutai-labs/moshi)\]\[[LLaMA-Omni](https://github.com/ictnlp/LLaMA-Omni)\]\[[OpenOmni](https://github.com/RainBowLuoCS/OpenOmni)\]\[[Voila](https://arxiv.org/abs/2505.02707)\]\[[MGM-Omni](https://github.com/dvlab-research/MGM-Omni)\]
      • [blog - Audio)\]\[[Qwen-Audio](https://github.com/QwenLM/Qwen-Audio)\]\[[Qwen2.5-Omni](https://github.com/QwenLM/Qwen2.5-Omni)\]\[[Qwen3-Omni](https://github.com/QwenLM/Qwen3-Omni)\]\[[CoGenAV](https://github.com/HumanMLLM/CoGenAV)\]
      • [paper - TTS)\]\[[FireRedTTS](https://github.com/FireRedTeam/FireRedTTS)\]\[[FireRedTTS-2](https://github.com/FireRedTeam/FireRedTTS2)\]\[[FireRedASR](https://github.com/FireRedTeam/FireRedASR)\]\[[FireRedChat](https://github.com/FireRedTeam/FireRedChat)\]\[[Seed-TTS](https://arxiv.org/abs/2406.02430)\]\[[IndexTTS](https://arxiv.org/abs/2502.05512)\]\[[MegaTTS3](https://github.com/bytedance/MegaTTS3)\]\[[TangoFlux](https://github.com/declare-lab/TangoFlux)\]\[[F5R-TTS](https://arxiv.org/abs/2504.02407)\]\[[Muyan-TTS](https://github.com/MYZY-AI/Muyan-TTS)\]\[[ZipVoice](https://github.com/k2-fsa/ZipVoice)\]
      • [paper
      • [paper
      • [speech-trident - ai/outspeed)\]\[[VideoChat](https://github.com/Henry-23/VideoChat)\]\[[MMAudio](https://github.com/hkchengrex/MMAudio)\]\[[pipecat](https://github.com/pipecat-ai/pipecat)\]\[[PDF2Audio](https://github.com/lamm-mit/PDF2Audio)\]\[[Open-LLM-VTuber](https://github.com/Open-LLM-VTuber/Open-LLM-VTuber)\]
      • [paper
      • [paper - Audio)\]\[[Higgs Audio V2](https://github.com/boson-ai/higgs-audio)\]\[[MiMo-Audio](https://github.com/XiaomiMiMo/MiMo-Audio)\]
      • [paper - ai/Step-Audio)\]\[[Step-Audio2](https://github.com/stepfun-ai/Step-Audio2)\]\[[Step-Audio-EditX](https://github.com/stepfun-ai/Step-Audio-EditX)\]\[[ACE-Step](https://github.com/ace-step/ACE-Step)\]\[[Baichuan-Audio](https://arxiv.org/abs/2502.17239)\]\[[MiniMax-Speech](https://arxiv.org/abs/2505.07916)\]\[[Audio Flamingo 3](https://arxiv.org/abs/2507.08128)\]\[[Voxtral](https://arxiv.org/abs/2507.13264)\]
      • [paper - 4-Voice)\]\[[VoxCPM](https://github.com/OpenBMB/VoxCPM)\]
      • [paper - rl/slamkit)\]\[[Llasa](https://arxiv.org/abs/2502.04128)\]
      • [paper
      • [paper - Speech-Tokenizer](https://github.com/HeCheng0625/Diffusion-Speech-Tokenizer)\]
      • [paper - bain/whisperX)\]
      • [blog
      • [paper - E-X](https://github.com/Plachtaa/VALL-E-X)\]\[[edge-tts](https://github.com/rany2/edge-tts)\]\[[VibeVoice](https://github.com/microsoft/VibeVoice)\]
      • [paper - mmlab/Amphion)\]\[[FoleyCrafter](https://github.com/open-mmlab/FoleyCrafter)\]\[[vta-ldm](https://github.com/ariesssxu/vta-ldm)\]\[[MMAudio](https://github.com/hkchengrex/MMAudio)\]\[[Kling-Foley](https://arxiv.org/abs/2506.19774)\]\[[ThinkSound](https://github.com/FunAudioLLM/ThinkSound)\]\[[video-SALMONN-2](https://github.com/bytedance/video-SALMONN-2)\]\[[AudioStory](https://github.com/TencentARC/AudioStory)\]\[[HunyuanVideo-Foley](https://github.com/Tencent-Hunyuan/HunyuanVideo-Foley)\]
      • [paper - VITS2](https://github.com/fishaudio/Bert-VITS2)\]\[[so-vits-svc-fork](https://github.com/voicepaw/so-vits-svc-fork)\]\[[GPT-SoVITS](https://github.com/RVC-Boss/GPT-SoVITS)\]\[[VITS-fast-fine-tuning](https://github.com/Plachtaa/VITS-fast-fine-tuning)\]
      • [paper - ai/OpenVoice)\]\[[MockingBird](https://github.com/babysor/MockingBird)\]\[[clone-voice](https://github.com/jianchang512/clone-voice)\]\[[Real-Time-Voice-Cloning](https://github.com/CorentinJ/Real-Time-Voice-Cloning)\]
      • [paper - tts-pytorch](https://github.com/lucidrains/e2-tts-pytorch)\]
      • [paper
      • [paper - Omni](https://github.com/ictnlp/LLaMA-Omni)\]\[[LLaMA-Omni2](https://github.com/ictnlp/LLaMA-Omni2)\]\[[SLED-TTS](https://github.com/ictnlp/SLED-TTS)\]\[[Stream-Omni](https://github.com/ictnlp/Stream-Omni)\]\[[SpeechGPT](https://github.com/0nutation/SpeechGPT)\]\[[SpeechGPT-2.0-preview](https://github.com/OpenMOSS/SpeechGPT-2.0-preview)\]\[[MOSS-TTSD](https://github.com/OpenMOSS/MOSS-TTSD)\]
      • [paper
      • [paper - TTS)\]\[[VoxBox](https://github.com/SparkAudio/VoxBox)\]
      • [paper - speech)\]\[[Bert-VITS2](https://github.com/fishaudio/Bert-VITS2)\]
      • [paper - art-projection/YuE)\]\[[MuQ](https://github.com/tencent-ailab/MuQ)\]\[[SongGeneration](https://github.com/tencent-ailab/SongGeneration)\]\[[SongBloom](https://github.com/tencent-ailab/SongBloom)\]\[[musiclm-pytorch](https://github.com/lucidrains/musiclm-pytorch)\]\[[Seed-Music](https://arxiv.org/abs/2409.09214)\]\[[XMusic](https://arxiv.org/abs/2501.08809)\]\[[MusicGen](https://github.com/facebookresearch/audiocraft/blob/main/docs/MUSICGEN.md)\]\[[InspireMusic](https://github.com/FunAudioLLM/InspireMusic)\]\[[SongGen](https://github.com/LiuZH-19/SongGen)\]\[[NotaGen](https://github.com/ElectricAlexis/NotaGen)\]\[[DiffRhythm](https://github.com/ASLP-lab/DiffRhythm)\]\[[MusiCoT](https://musicot.github.io)\]\[[ACE-Step](https://github.com/ace-step/ACE-Step)\]
      • [paper
      • [paper
      • [paper - audio)\]
      • [paper - TTS)\]

  • GNN

    • 2. LLM for decision making

      • [paper
      • [paper - pytorch](https://github.com/zfjsail/gae-pytorch)\]
      • [paper
      • [paper
      • [paper - /GAT)\]\[[pyGAT](https://github.com/Diego999/pyGAT)\]\[[pytorch-GAT](https://github.com/gordicaleksa/pytorch-GAT)\]
      • [paper - gnns)\]
      • [paper - Bert](https://github.com/jwzhanggy/Graph-Bert)\]\[[(G2PT](https://arxiv.org/abs/2501.01073)\]
      • [paper - LLM4Graph-Papers)\]
      • [GNNPapers
      • [pytorch_geometric - Recommender-Systems](https://github.com/tsinghua-fib-lab/GNN-Recommender-Systems)\]
      • [paper
      • [link

  • Transformer Architecture

    • Survey for GNN

      • [paper - embedding-torch](https://github.com/lucidrains/rotary-embedding-torch)\]\[[rerope](https://github.com/bojone/rerope)\]\[[blog](https://kexue.fm/archives/9675)\]\[[positional_embedding](https://skylyj.github.io/positional_embedding/)\]\[[longformer](https://github.com/allenai/longformer)\]
      • [paper - spaces/mamba)\]\[[Transformers are SSMs](https://arxiv.org/abs/2405.21060)\]\[[mamba-minimal](https://github.com/johnma2006/mamba-minimal)\]\[[Awesome-Mamba-Papers](https://github.com/yyyujintang/Awesome-Mamba-Papers)\]\[[Falcon Mamba](https://arxiv.org/abs/2410.05355)\]\[[H-Net](https://github.com/goombalab/hnet)\]\[[A Systematic Analysis of Hybrid Linear Attention](https://arxiv.org/abs/2507.06457)\]\[[flash-linear-attention](https://github.com/fla-org/flash-linear-attention)\]
      • [paper - query-attention-pytorch)\]\[[MLA blog](https://kexue.fm/archives/10091)\]\[[MLA blog](https://kexue.fm/archives/10907)\]\[[FlashMLA](https://github.com/deepseek-ai/FlashMLA)\]\[[MFA](https://arxiv.org/abs/2412.19255)\]\[[TPA](https://arxiv.org/abs/2501.06425)\]\[[Sigma](https://arxiv.org/abs/2501.13629)\]\[[TransMLA](https://github.com/fxmeng/TransMLA)\]\[[MHA2MLA](https://github.com/JT-Ushio/MHA2MLA)\]\[[MTLA](https://github.com/D-Keqi/mtla)\]
      • [paper - HPC-AI-Lab/Neural-Network-Diffusion)\]\[[GPD](https://github.com/tsinghua-fib-lab/GPD)\]\[[tree-diffusion](https://github.com/revalo/tree-diffusion)\]
      • [paper - deepmind/recurrentgemma)\]
      • [paper - AI/xlstm)\]\[[vision-lstm](https://github.com/NX-AI/vision-lstm)\]\[[xLSTM 7B](https://arxiv.org/abs/2503.13427)\]\[[PyxLSTM](https://github.com/muditbhargava66/PyxLSTM)\]\[[xlstm-cuda](https://github.com/smvorwerk/xlstm-cuda)\]\[[Attention as an RNN](https://arxiv.org/abs/2405.13956)\]\[[Were RNNs All We Needed](https://arxiv.org/abs/2410.01201)\]
      • [paper - kan](https://github.com/Blealtan/efficient-kan)\]\[[kan-gpt](https://github.com/AdityaNG/kan-gpt)\]\[[Convolutional-KANs](https://github.com/AntonioTepsich/Convolutional-KANs)\]\[[kat](https://github.com/Adamdad/kat)\]\[[FAN](https://github.com/YihongDong/FAN)\]
      • [paper - v0.1)\]\[[Samba](https://github.com/microsoft/Samba)\]\[[TransMamba](https://arxiv.org/abs/2503.24067)\]\[[Nemotron-H](https://arxiv.org/abs/2504.03624)\]
      • [paper - lm-pytorch](https://github.com/test-time-training/ttt-lm-pytorch)\]\[[marc](https://github.com/ekinakyurek/marc)\]\[[Titans: Learning to Memorize at Test Time](https://arxiv.org/abs/2501.00663)\]\[[titans-pytorch](https://github.com/lucidrains/titans-pytorch)\]\[[Test-Time Training with Self-Supervision for Generalization under Distribution Shifts](https://arxiv.org/abs/1909.13231)\]\[[ATLAS](https://arxiv.org/abs/2505.23735)\]
      • [paper - LM)\]\[[Awesome-RWKV-in-Vision](https://github.com/Yaziwel/Awesome-RWKV-in-Vision)\]\[[RWKV-7](https://arxiv.org/abs/2503.14456)\]
      • [paper
      • [paper - pytorch](https://github.com/lucidrains/native-sparse-attention-pytorch)\]\[[native-sparse-attention](https://github.com/fla-org/native-sparse-attention)\]\[[flash-linear-attention](https://github.com/fla-org/flash-linear-attention)\]\[[FSA](https://github.com/Relaxed-System-Lab/Flash-Sparse-Attention)\]
      • [paper
      • [paper
      • [website - LM)\]\[[ChatRWKV](https://github.com/BlinkDL/ChatRWKV)\]\[[rwkv.cpp](https://github.com/RWKV/rwkv.cpp)\]
      • [paper - W/TokenFormer)\]
      • [website - LM)\]\[[ChatRWKV](https://github.com/BlinkDL/ChatRWKV)\]\[[rwkv.cpp](https://github.com/RWKV/rwkv.cpp)\]
Programming Languages
Python 83 Jupyter Notebook 8 C++ 3 TypeScript 2 HTML 2 JavaScript 1 Shell 1 SCSS 1
Categories
NLP 1,581 Multimodal 303 CV 147 Reinforcement Learning 31 Transformer Architecture 17 GNN 12
Sub Categories
3. Pretraining 1,564 5. Multimodal LLM 82 4. Diffusion Model 49 7. Text2Video 48 1. Audio 41 6. Text2Image 34 3. CV Application 27 1.Basic for RL 25 5. Generative Model (GAN and VAE) 20 4. Foundation Model 19 9. Video 18 2. LLM for decision making 18 6. Image Editing 18 Survey for GNN 17 3. Clip 17 8. Semantic Segmentation 16 2. Blip 13 7. Object Detection 13 1. Word2Vec 11 9. Other 10 8. Survey for Multimodal 9 1. Basic for CV 8 2. Contrastive Learning 6 2. Seq2Seq 6 10. Survey for CV 2
Keywords
llm 28 pytorch 23 deep-learning 17 ai 14 machine-learning 13 python 12 llama 11 chatgpt 10 nlp 10 large-language-models 9 rag 8 evaluation 6 artificial-intelligence 6 llama3 5 openai 5 qwen 5 tensorflow 5 agents 5 diffusion 4 chatglm 4 retrieval-augmented-generation 4 llama2 4 transformers 4 stable-diffusion 4 fine-tuning 3 image-generation 3 gpt 3 inference 3 transformer 3 gemma 3 data-science 3 llm-inference 3 mistral 3 bert 3 rlhf 3 computer-vision 3 benchmark 3 llms 3 natural-language-processing 3 lora 3 gemini 2 ai-agents 2 prompt 2 chatbot 2 survey 2 language-model 2 awsome-list 2 deepseek-r1 2 voice-conversion 2 video-generation 2