{"id":132800,"url":"https://github.com/operator22th/awesome-world-models-for-robots","name":"awesome-world-models-for-robots","description":"Awesome World Model for Robotics Papers","projects_count":103,"last_synced_at":"2026-08-31T02:00:33.627Z","repository":{"id":274125100,"uuid":"921979468","full_name":"operator22th/awesome-world-models-for-robots","owner":"operator22th","description":"Awesome World Model for Robotics Papers","archived":false,"fork":false,"pushed_at":"2026-03-30T07:01:28.000Z","size":82,"stargazers_count":139,"open_issues_count":0,"forks_count":5,"subscribers_count":4,"default_branch":"main","last_synced_at":"2026-08-11T12:12:06.680Z","etag":null,"topics":["robotics","world-model"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/operator22th.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-01-25T02:13:59.000Z","updated_at":"2026-07-25T17:15:17.000Z","dependencies_parsed_at":"2026-03-30T09:10:31.167Z","dependency_job_id":null,"html_url":"https://github.com/operator22th/awesome-world-models-for-robots","commit_stats":null,"previous_names":["operator22th/awesome-world-models-for-robots"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/operator22th/awesome-world-models-for-robots","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/operator22th%2Fawesome-world-models-for-robots","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/operator22th%2Fawesome-world-models-for-robots/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/operator22th%2Fawesome-world-models-for-robots/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/operator22th%2Fawesome-world-models-for-robots/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/operator22th","download_url":"https://codeload.github.com/operator22th/awesome-world-models-for-robots/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/operator22th%2Fawesome-world-models-for-robots/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":36990945,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-22T15:14:58.755Z","status":"online","status_checked_at":"2026-08-31T02:00:07.497Z","response_time":119,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2026-05-31T03:30:13.898Z","updated_at":"2026-08-31T02:00:33.628Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["related: LLM as WM","related: RL in the Real World","related: Robotics \u0026 Vision-based RL","related: Robotics \u0026 Foundation models","related: World Models","related: Robotics \u0026 Visual representations","dataset","papers","toolbox","related: Generative simulation","related: Generative models for Decision-Making","overview","workshop","benchmark","models","related: Transfer Learning"],"sub_categories":[],"readme":"# awesome-world-models-for-robots\n## overview\n- [World Models](https://www.nvidia.com/en-us/glossary/world-models/)\n- arxiv 2024, 11, Understanding World or Predicting Future? A Comprehensive Survey of World Models [Paper](https://arxiv.org/pdf/2411.14499).\n## benchmark\n- arXiv 2024, 03, HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation [Paper](https://arxiv.org/abs/2403.10506) [Website](https://sferrazza.cc/humanoidbench_site/). $15$ whole-body manipulation and $12$ locomotion tasks. This repo contains the code for environments and training.\n## dataset\n- Pysical AI [Website](https://huggingface.co/collections/nvidia/physical-ai-67c643edbb024053dcbcd6d8).\n- AgiBot World [Website](https://github.com/OpenDriveLab/AgiBot-World). 1 million+ trajectories from 100 robots.\n- LeRobotDataset [Website](https://github.com/huggingface/lerobot). A bunch of models, datasets, and tools for real-world robotics in PyTorch.\n- 1xgpt [Website](https://github.com/1x-technologies/1xgpt).\n- OXE [Paper](https://arxiv.org/abs/2310.08864).\n## models\n- V-JEPA2 [Website](https://ai.meta.com/vjepa/). [Paper](https://arxiv.org/abs/2506.09985) [Code](https://github.com/facebookresearch/vjepa2).\n- Cosmos [Website](https://developer.nvidia.com/cosmos). [Paper](https://arxiv.org/abs/2501.03575). Autoregressive Video2World/Text2World foundation models.\n## toolbox\n- Menagerie [Website](https://github.com/google-deepmind/mujoco_menagerie) MuJoCo physics engines. System identification toolbox has not been released.(up to 2025.1)\n- MuJoCo Playground [Website](https://playground.mujoco.org/) [Paper](https://playground.mujoco.org/assets/playground_technical_report.pdf) Training environments in mjx. Humanoid Locomotion, Quadruped Locomotion and Manipulation (most robot arms and hand) tasks are included.\n## papers\n- arxiv 2026, 02, World Action Models are Zero-shot Policies. [Webiste](https://dreamzero0.github.io/). [Paper](https://arxiv.org/abs/2602.15922).\n- arxiv 2026, 01, PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation. [Website](https://point-world.github.io/). [Paper](https://arxiv.org/abs/2601.03782).\n- arxiv 2026, 01, Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning. [Paper](https://arxiv.org/abs/2601.16163). [Website](https://research.nvidia.com/labs/dir/cosmos-policy/).\n- arxiv 2025, 12, What Drives Success in Physical Planning with Joint-Embedding Predictive World Models? [Paper](https://www.arxiv.org/abs/2512.24497). [Code](https://github.com/facebookresearch/jepa-wms).\n- arxiv 2025, 12, World Models Can Leverage Human Videos for Dexterous Manipulation. [Paper](https://arxiv.org/abs/2512.13644). [Website](https://raktimgg.github.io/dexwm/).\n- arxiv 2025, 12, Closing the Train-Test Gap in World Models for Gradient-Based Planning. [Paper](https://arxiv.org/abs/2512.09929). [Code](https://github.com/qw3rtman/robust-world-model-planning).\n- arxiv 2025, 10, Ego-Vision World Model for Humanoid Contact Planning. [Website](https://ego-vcp.github.io/).\n- unitree world model, UnifoLM-WMA-0: A World-Model-Action (WMA) Framework under UnifoLM Family. [Website](https://unigen-x.github.io/unifolm-world-model-action.github.io/).\n- arxiv 2025, 08, Genie Envisioner: A Unified World Foundation Model for Robotic Manipulation. [Website](https://genie-envisioner.github.io/). [Paper](https://arxiv.org/abs/2508.05635).\n- RSS 2025 Best Systems Paper finalist, Learned Perceptive Forward Dynamics Model for Safe and Platform-aware Robotic Navigation. [Website](https://leggedrobotics.github.io/fdm.github.io/). [Paper](https://arxiv.org/abs/2504.19322).\n- RSS 2025, Particle-Grid Neural Dynamics for Learning Deformable Object Models from RGB-D Videos. [Website](https://kywind.github.io/pgnd). [Paper](https://arxiv.org/abs/2506.15680).\n- 1x-world-model. [Paper](https://www.1x.tech/1x-world-model.pdf).\n- arxiv 2025, 05, Evaluating Robot Policies in a World Model. [Paper](https://arxiv.org/abs/2506.00613).\n- arxiv 2025, 05, RLVR-World: Training World Models with Reinforcement Learning. [Paper](https://arxiv.org/abs/2505.13934).\n- arxiv 2025, 04, TesserAct: Learning 4D Embodied World Models. [Website](https://tesseractworld.github.io/).\n- arxiv 2025, 02, Strengthening Generative Robot Policies through Predictive World Modeling. [Paper](https://arxiv.org/pdf/2502.00622). Stengthen imitation learning with world model.\n- RSS 2025, Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets. [Website](https://weirdlabuw.github.io/uwm/).\n- RSS 2025, Unified Video Action Model. [Website](https://unified-video-action-model.github.io/).\n- ICRA 2025, World Model-based Perception for Visual Legged Locomotion. [Website](https://wmp-loco.github.io/). [Code](https://github.com/bytedance/WMP).\n- arxiv 2025, 03, Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning. [Paper](https://arxiv.org/abs/2503.01837). [Website](https://adrialopezescoriza.github.io/demo3/).\n- arxiv 2025, 01, RoboHorizon: An LLM-Assisted Multi-View World Model for Long-Horizon Robotic Manipulation [Papaer](https://arxiv.org/abs/2501.06605).\n- arxiv 2025, 01, Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics [Paper](https://arxiv.org/abs/2501.10100v1). MBPO sim2real using world models. Quadruped locomotion tasks.\n- ICML 2025, Trajectory World Models for Heterogeneous Environments. [Paper](https://arxiv.org/abs/2502.01366).\n- ICLR 2025 (Spotlight), DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes. [Website](https://dynamic-city.github.io/).\n- CVPR 2025 (Oral), Navigation World Models. [Website](https://www.amirbar.net/nwm/). [Paper](https://arxiv.org/abs/2412.03572).\n- ICRA 2024, MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation. [Paper](https://arxiv.org/pdf/2309.14236).\n- CoRL 2024, Multi-Task Interactive Robot Fleet Learning with Visual World Models. [Paper](https://arxiv.org/pdf/2410.22689). Visual world model for anomaly detection.\n- Neulps 2024, iVideoGPT: Interactive VideoGPTs are Scalable World Models. [Website](https://thuml.github.io/iVideoGPT/). [Code](https://github.com/thuml/iVideoGPT).\n- RSS 2024, HRP: Human Affordances for Robotic Pre-Training. [Paper](https://arxiv.org/abs/2407.18911).\n- ICLR 2024 (Outstanding Paper), UniSim: Learning Interactive Real-World Simulators [Website](https://universal-simulator.github.io/unisim/).\n- ICLR 2024, Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation [Website](https://gr1-manipulation.github.io/).\n- arxiv 2024, 11, DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning. [Website](https://dino-wm.github.io/). World model for MPC. DINOv2 for representation.\n- CVPR 2023, Affordances from Human Videos as a Versatile Representation for Robotics. [Paper](https://arxiv.org/abs/2304.08488). Prediction contact points and trajectory waypoints, then use it for downstream tasks (suitable for different learning paradigms).\n- RSS 2023, Structured World Models from Human Videos. [Paper](https://arxiv.org/abs/2308.10901). Robot arm manipulation tasks. World Models with structured action space design.\n- CoRL 2023 (Oral), Finetuning Offline World Models in the Real World [Website](https://www.yunhaifeng.com/FOWM/) [Paper](https://arxiv.org/abs/2310.16029) Offline pretraining and online finetuning of world models. Robot arm manipulation tasks.\n- CoRL 2022, Daydreamer: World models for physical robot learning. [Paper](https://arxiv.org/abs/2206.14176).\n## workshop\n- Neurlps 2025, Embodied World Models for Decision Making [Website](https://embodied-world-models.github.io/).\n- CoRL 2025, Robotics World Modeling [Website](https://robot-world-modeling.github.io/).\n- ICCV 2025, Reliable and Interactive World Model [Website](https://riwm-2025.github.io/RIWM-2025/).\n- RSS 2025, Structured World Models for Robotic Manipulation [Website](https://swomo-rss.github.io/).\n- ICML 2024, Multi-modal Foundation Model meets Embodied AI [Website](https://icml-mfm-eai.github.io/).\n- ICLR 2025, Generative Models for Robot Learning. [Website](https://genbot-workshop.github.io/).\n- ICLR 2025, World Models. [Website](https://sites.google.com/view/worldmodel-iclr2025/).\n- ICML 2025, Building Physically Plausible World Models. [Website](https://physical-world-modeling.github.io/).\n## related: World Models\n- Leo Fan's List. [Website](https://github.com/leofan90/Awesome-World-Models).\n- ICML 2025 (Oral), Temporal Difference Flows. [Paper](https://arxiv.org/abs/2503.09817).\n- ICML 2025 (Spotlight), Novelty Detection in Reinforcement Learning with World Models. [Paper](https://arxiv.org/abs/2310.08731v4).\n- arxiv 2025, 03, Denoising Hamiltonian Network for Physical Reasoning. [Paper](https://arxiv.org/abs/2503.07596).\n- arxiv 2024, 05, Hierarchical World Models as Visual Whole-Body Humanoid Controllers. [Website](https://www.nicklashansen.com/rlpuppeteer/).\n- ICML 2024, Offline Transition Modeling via Contrastive Energy Learning. [Code](https://github.com/Ruifeng-Chen/Energy-Transition-Models).\n- ICML 2024, 3D-VLA: A 3DVision-Language-Action Generative World Model. [Paper](https://arxiv.org/pdf/2403.09631).\n- ICML 2024 (Oral), Genie: Generative Interactive Environments. [Paper](https://arxiv.org/abs/2402.15391).\n- ICML 2024 (Oral), Learning to Model the World with Language. [Paper](https://arxiv.org/abs/2308.01399). [Website](https://dynalang.github.io/).\n- 2024, 12, Genie2 [Blog](https://deepmind.google/discover/blog/genie-2-a-large-scale-foundation-world-model/).\n- ICML 2025, PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop. [Paper](https://arxiv.org/pdf/2503.09595). [Webstite](https://vision-x-nyu.github.io/pisa-experiments.github.io/).\n## related: LLM as WM\n- ICLR 2025, Monte Carlo Planning with Large Language Model for Text-Based Games. [Paper](https://openreview.net/forum?id=r1KcapkzCt).\n- arxiv 2024, AgentGym: Evolving Large Language Model-based Agents across Diverse Environments. [Paper](https://arxiv.org/abs/2406.04151). [Code](https://github.com/WooooDyy/AgentGym).\n- NIPS 2023, Language Models Meet World Models: Embodied Experiences Enhance Language Models. [Paper](https://arxiv.org/abs/2305.10626). [Openreview](https://openreview.net/forum?id=SVBR6xBaMl).\n- NIPS 2023, Large Language Models as Commonsense Knowledge for Large-Scale Task Planning. [Website](https://llm-mcts.github.io/). [Paper](https://arxiv.org/abs/2305.14078).\n- NIPS 2023, ChessGPT: Bridging Policy Learning and Language Modeling. [Paper](https://arxiv.org/abs/2306.09200). [Code](https://github.com/waterhorse1/ChessGPT).\n## related: Transfer Learning\n- arxiv 2022, 01, Transferability in Deep Learning: A Survey. [Paper](https://arxiv.org/abs/2201.05867).\n## related: Robotics \u0026 Foundation models\n- 2025, 03,  GR00T N1: An Open Foundation Model for Generalist Humanoid Robots. [Code](https://github.com/NVIDIA/Isaac-GR00T).\n- RSS 2024, OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics. [Paper](https://arxiv.org/pdf/2401.12202).\n- CoRL 2023 (Oral), VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models. [Website](https://voxposer.github.io/).\n- ICLR 2024, Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models. [Paper](https://arxiv.org/abs/2310.10639).\n- ICRA 2025, WildLMA: Long Horizon Loco-MAnipulation in the Wild. [Website](https://wildlma.github.io/).\n- arxiv, 2024, 12, NaVILA: Legged Robot Vision-Language-Action Model for Navigation. [Website](https://navila-bot.github.io/).\n- arxiv, 2024, 10, GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs. [Paper](https://arxiv.org/pdf/2410.03645).\n## related: Robotics \u0026 Vision-based RL\n- CoRL 2022 (Oral), Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion. [Paper](https://arxiv.org/abs/2210.10044).\n- CoRL 2022 (Oral), Legged Locomotion in Challenging Terrains using Egocentric Vision. [Paper](https://arxiv.org/pdf/2211.07638).\n- ICML 2023 (Oral), Efficient RL via Disentangled Environment and Agent Representations. [Website](https://sear-rl.github.io/).\n- CoRL 2022, VideoDex: Learning Dexterity from Internet Videos. [Website](https://video-dex.github.io/).\n- CVPR 2022, Coupling Vision and Proprioception for Navigation of Legged Robots. [Paper](https://arxiv.org/abs/2112.02094).\n- CoRL 2024, Continuously Improving Mobile Manipulation with Autonomous Real-World RL. [Paper](https://arxiv.org/abs/2409.20568). Mobile Manipulation.\n- RSS 2023, Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials. [Paper](https://arxiv.org/abs/2210.05178).\n- CoRL 2024, Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance. [Website](https://nakamotoo.github.io/V-GPS/).\n## related: Robotics \u0026 Visual representations\n- NeurIPS 2024, DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control. [Paper](https://arxiv.org/pdf/2409.12192).\n- RSS 2024, HRP: Human Affordances for Robotic Pre-Training. [Paper](https://arxiv.org/abs/2407.18911).\n- ICML 2023 (Oral), Efficient RL via Disentangled Environment and Agent Representations. [Website](https://sear-rl.github.io/).\n- CVPR 2023, Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture. [Paper](https://arxiv.org/abs/2301.08243).\n- ICML 2022, On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline. [Paper](https://arxiv.org/abs/2212.05749).\n- IROS 2023, Visual Reinforcement Learning with Self-Supervised 3D Representations. [Paper](https://arxiv.org/abs/2210.07241).\n## related: Generative models for Decision-Making\n- ICML 2025, History-Guided Video Diffusion. [Website](https://boyuan.space/history-guidance/). [Paper](https://arxiv.org/abs/2502.06764).\n- arxiv 2025, 01, Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review. [Paper](https://arxiv.org/abs/2501.09685).\n- arxiv 2024, 05, Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models. [Paper](https://arxiv.org/abs/2405.19673).\n- NIPS 2024, Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion. [Website](https://boyuan.space/diffusion-forcing/).\n- ICML 2022, Learning Iterative Reasoning through Energy Minimization. [Paper](https://arxiv.org/abs/2206.15448).\n- ICRA 2023, NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration. [Paper](https://arxiv.org/abs/2310.07896).\n- ICML 2024, Video as the New Language for Real-World Decision Making. [Paper](https://arxiv.org/abs/2402.17139).\n## related: Generative simulation\n- arxiv 2024, 06, RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots. [Paper](https://arxiv.org/abs/2406.02523).\n## related: RL in the Real World\n- arxiv 2021, 02, NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning. [Paper](https://arxiv.org/abs/2102.00714). [Website](http://polixir.ai/research/neorl)\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/operator22th%2Fawesome-world-models-for-robots/projects"}