{"id":20301342,"url":"https://github.com/songqiang321/time-series-papers","last_synced_at":"2026-03-06T07:03:27.201Z","repository":{"id":214451539,"uuid":"736561093","full_name":"songqiang321/Time-Series-Papers","owner":"songqiang321","description":"This is a repository for collecting papers and code in time series domain.","archived":false,"fork":false,"pushed_at":"2026-02-18T03:35:20.000Z","size":176,"stargazers_count":40,"open_issues_count":0,"forks_count":5,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-02-18T08:11:49.895Z","etag":null,"topics":["ai-for-time-series","data-science","deep-learning","llm-for-time-series","machine-learning","time-series","time-series-analysis","time-series-forecasting","time-series-prediction","transformer"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/songqiang321.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2023-12-28T08:34:04.000Z","updated_at":"2026-02-18T03:35:23.000Z","dependencies_parsed_at":"2024-03-24T10:23:16.151Z","dependency_job_id":"e157b498-710f-44e0-aa5d-654d3b75ac05","html_url":"https://github.com/songqiang321/Time-Series-Papers","commit_stats":null,"previous_names":["songqiang321/time-series-papers"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/songqiang321/Time-Series-Papers","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/songqiang321%2FTime-Series-Papers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/songqiang321%2FTime-Series-Papers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/songqiang321%2FTime-Series-Papers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/songqiang321%2FTime-Series-Papers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/songqiang321","download_url":"https://codeload.github.com/songqiang321/Time-Series-Papers/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/songqiang321%2FTime-Series-Papers/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30164903,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-06T04:43:31.446Z","status":"ssl_error","status_checked_at":"2026-03-06T04:40:30.133Z","response_time":250,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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"}},"keywords":["ai-for-time-series","data-science","deep-learning","llm-for-time-series","machine-learning","time-series","time-series-analysis","time-series-forecasting","time-series-prediction","transformer"],"created_at":"2024-11-14T16:25:26.187Z","updated_at":"2026-03-06T07:03:27.194Z","avatar_url":"https://github.com/songqiang321.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Time-Series-Papers\nThis is a repository for collecting papers and code in time series domain.\n\n## Table of Content  \n\n- [Linear](#linear)\n- [RNN and CNN](#rnn-and-cnn)\n- [Transformer](#transformer)\n- [GNN](#gnn)\n- [LLM Framework](#llm-framework)\n- [Diffusion Model](#diffusion-model)\n- [Benchmark and Dataset](#benchmark-and-dataset)\n- [Repositories](#repositories)\n\n```bash\n  ├─ Linear/  \n  ├─ RNN and CNN/           \n  ├─ Transformer/\n  ├─ GNN/\n  ├─ LLM Framework/\n  ├─ Diffusion Model/\n  ├─ Benchmark and Dataset/                      \n  └─ Repositories/         \n```\n\n---\n\n## Linear\n\n- **N-BEATS: Neural basis expansion analysis for interpretable time series forecasting**, _Oreshkin et al._, ICLR 2020. \\[[paper](https://arxiv.org/abs/1905.10437)\\]\\[[n-beats](https://github.com/philipperemy/n-beats)\\]\\[[N-BEATS](https://github.com/ServiceNow/N-BEATS)\\]\n- DLinear: **Are Transformers Effective for Time Series Forecasting**, _Zeng et al._, AAAI 2023. \\[[paper](https://arxiv.org/abs/2205.13504)\\]\\[[code](https://github.com/cure-lab/LTSF-Linear)\\]\\[[DiPE-Linear](https://github.com/wintertee/DiPE-Linear)\\]\\[[TimeLinear](https://github.com/zclzcl0223/TimeLinear)\\]\n- **TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting**, _Ekambaram et al._, KDD 2023. \\[[paper](https://arxiv.org/abs/2306.09364)\\]\\[[model](https://huggingface.co/docs/transformers/main/en/model_doc/patchtsmixer)\\]\\[[example](https://github.com/ibm/tsfm#notebooks-links)\\]\n- FreTS: **Frequency-domain MLPs are More Effective Learners in Time Series Forecasting**, _Yi et al._, NeurIPS 2023. \\[[paper](https://arxiv.org/abs/2311.06184)\\]\\[[code](https://github.com/aikunyi/FreTS)\\]\\[[FilterNet](https://github.com/aikunyi/FilterNet)\\]\n- **Tiny Time Mixers (TTMs): Fast Pretrained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series**, _Ekambaram et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2401.03955)\\]\\[[code](https://github.com/ibm-granite/granite-tsfm/tree/main/tsfm_public/models/tinytimemixer)\\]\n- **FCDNet: Frequency-Guided Complementary Dependency Modeling for Multivariate Time-Series Forecasting**, _Chen et al._, arxiv 2023. \\[[paper](https://arxiv.org/abs/2312.16450)\\]\\[[code](https://github.com/onceCWJ/FCDNet)\\]\n- **SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion**, _Han et al._, NeurIPS 2024. \\[[paper](https://arxiv.org/abs/2404.14197)\\]\\[[code](https://github.com/Secilia-Cxy/SOFTS)\\]\n- **SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters**, _Lin et al._, ICML 2024 Oral. \\[[paper](https://arxiv.org/abs/2405.00946)\\]\\[[code](https://github.com/lss-1138/SparseTSF)\\]\n- **TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting**, _Wang et al._, ICLR 2024. \\[[paper](https://arxiv.org/abs/2405.14616)\\]\\[[code](https://github.com/kwuking/TimeMixer)\\]\n- **DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting**, _Qiu et al._, KDD 2025. \\[[paper](https://arxiv.org/abs/2412.10859)\\]\\[[code](https://github.com/decisionintelligence/DUET)\\]\n\n---\n\n## RNN and CNN\n\n- **DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks**, _Salinas et al._, arxiv 2017. \\[[paper](https://arxiv.org/abs/1704.04110)\\]\\[[TimeSeries](https://github.com/zhykoties/TimeSeries)\\]\n- **TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis**, _Wu et al._, ICLR 2023. \\[[paper](https://arxiv.org/abs/2210.02186)\\]\\[[code](https://github.com/thuml/TimesNet)\\]\\[[slides](https://wuhaixu2016.github.io/pdf/ICLR2023_TimesNet.pdf)\\]\n- **RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks**, _Hou and Yu_, arxiv 2024. \\[[paper](https://arxiv.org/abs/2401.09093)\\]\\[[code](https://github.com/howard-hou/RWKV-TS)\\]\n\n---\n\n## Transformer\n\n- **Transformers in Time Series: A Survey**, _Wen et al._, IJCAI 2023. \\[[paper](https://arxiv.org/abs/2202.07125)\\]\\[[code](https://github.com/qingsongedu/time-series-transformers-review)\\]\n- **Deep Time Series Models: A Comprehensive Survey and Benchmark**, _Wang et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2407.13278)\\]\\[[code](https://github.com/thuml/Time-Series-Library)\\]\n- **Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting**, _Zhou et al._, AAAI 2021 Best paper. \\[[paper](https://arxiv.org/abs/2012.07436)\\]\\[[code](https://github.com/zhouhaoyi/Informer2020)\\]\n- **Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting**, _Wu et al._, NeurIPS 2021. \\[[paper](https://arxiv.org/abs/2106.13008)\\]\\[[code](https://github.com/thuml/Autoformer)\\]\\[[slides](https://wuhaixu2016.github.io/pdf/NeurIPS2021_Autoformer.pdf)\\]\\[[ETSformer](https://github.com/salesforce/ETSformer)\\]\n- **Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy**, _Xu et al._, ICLR 2022. \\[[paper](https://arxiv.org/abs/2110.02642)\\]\\[[code](https://github.com/thuml/Anomaly-Transformer)\\]\\[[slides](https://wuhaixu2016.github.io/pdf/ICLR2022_Anomaly.pdf)\\]\\[[TranAD](https://github.com/imperial-qore/TranAD)\\]\n- **Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting**, _Liu et al._, NeurIPS 2022. \\[[paper](https://arxiv.org/abs/2205.14415)\\]\\[[code](https://github.com/thuml/Nonstationary_Transformers)\\]\n- **iTransformer: Inverted Transformers Are Effective for Time Series Forecasting**, _Liu et al._, ICLR 2024 Spotlight. \\[[paper](https://arxiv.org/abs/2310.06625)\\]\\[[code](https://github.com/thuml/iTransformer)\\]\n- **Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting**, _Liu et al._, ICLR 2022. \\[[paper](https://openreview.net/forum?id=0EXmFzUn5I)\\]\\[[code](https://github.com/ant-research/Pyraformer)\\]\n- **FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting**, _Zhou et al._, ICML 2022. \\[[paper](https://arxiv.org/abs/2201.12740)\\]\\[[code](https://github.com/MAZiqing/FEDformer)\\]\\[[DAMO-DI-ML](https://github.com/DAMO-DI-ML)\\]\n- PatchTST: **A Time Series is Worth 64 Words: Long-term Forecasting with Transformers**, _Nie et al._, ICLR 2023. \\[[paper](https://arxiv.org/abs/2211.14730)\\]\\[[code](https://github.com/yuqinie98/PatchTST)\\]\n- **Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting**, _Zhang and Yan_, ICLR 2023.  \\[[paper](https://openreview.net/forum?id=vSVLM2j9eie)\\]\\[[code](https://github.com/Thinklab-SJTU/Crossformer)\\]\n- **TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables**, _Wang et al._, NeurIPS 2024. \\[[paper](https://arxiv.org/abs/2402.19072)\\]\\[[code](https://github.com/thuml/TimeXer)\\]\\[[code](https://github.com/thuml/TimeXer)\\]\n- **UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting**, _Liu et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2406.04975)\\]\n- MetaTST: **Metadata Matters for Time Series: Informative Forecasting with Transformers**, _Dong et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2410.03806)\\]\n- **Are Language Models Actually Useful for Time Series Forecasting**, _Tan et al._, NeurIPS 2024. \\[[paper](https://arxiv.org/abs/2406.16964)\\]\\[[code](https://github.com/BennyTMT/LLMsForTimeSeries)\\]\\[[CATS](https://github.com/dongbeank/CATS)\\]\n- **Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective**, _Wang et al._, NeurIPS 2024. \\[[paper](https://arxiv.org/abs/2409.18696)\\]\\[[code](https://github.com/ForestsKing/GLAFF)\\]\\[[ChatTime](https://github.com/ForestsKing/ChatTime)\\]\n- **ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer**, _Zhang et al._, NeurIPS 2024. \\[[paper](https://arxiv.org/abs/2411.01842)\\]\\[[code](https://github.com/microsoft/ProbTS/tree/elastst)\\]\n- **Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting**, _Chen et al._, ICLR 2024. \\[[paper](https://arxiv.org/abs/2402.05956)\\]\\[[code](https://github.com/decisionintelligence/pathformer)\\]\n- **MASTER: Market-Guided Stock Transformer for Stock Price Forecasting**, _Li et al._, AAAI 2024. \\[[paper](https://arxiv.org/abs/2312.15235)\\]\\[[code](https://github.com/SJTU-DMTai/MASTER)\\]\\[[StockMixer](https://github.com/SJTU-DMTai/StockMixer)\\]\\[[Quant-Reading-List](https://github.com/SJTU-DMTai/Quant-Reading-List)\\]\\[[UMI KDD 2025](https://arxiv.org/abs/2502.04737)\\]\n\n---\n\n## GNN\n\n- **A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection**, _Jin et al._, arxiv 2023. \\[[paper](https://arxiv.org/abs/2307.03759)\\]\\[[code](https://github.com/KimMeen/Awesome-GNN4TS)\\]\n- **GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks**, _Li et al._, NeurIPS 2023. \\[[paper](https://arxiv.org/abs/2311.04245)\\]\\[[code](https://github.com/HKUDS/GPT-ST)\\]\n- **FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective**, _Yi et al._, NeurIPS 2023. \\[[paper](https://arxiv.org/abs/2311.06190)\\]\\[[code](https://github.com/aikunyi/FourierGNN)\\]\n- **MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting**, _Cai et al._, AAAI 2024. \\[[paper](https://arxiv.org/abs/2401.00423)\\]\\[[code](https://github.com/YoZhibo/MSGNet)\\]\n\n---\n\n## LLM Framework\n\n- **Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook**, _Jin et al._, arxiv 2023. \\[[paper](https://arxiv.org/abs/2310.10196)\\]\\[[code](https://github.com/qingsongedu/Awesome-TimeSeries-SpatioTemporal-LM-LLM)\\]\n- **Large Language Models for Time Series: A Survey**, _Zhang et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2402.01801)\\]\\[[code](https://github.com/xiyuanzh/awesome-llm-time-series)\\]\\[[Empowering-Time-Series-Analysis-with-LLM](https://github.com/UConn-DSIS/Empowering-Time-Series-Analysis-with-LLM)\\]\n- **Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review**, _Su et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2402.10350)\\]\n\n- **SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling**, _Dong et al._, NeurIPS 2023 Spotlight. \\[[paper](https://arxiv.org/abs/2302.00861)\\]\\[[code](https://github.com/thuml/SimMTM)\\]\n- **One Fits All: Power General Time Series Analysis by Pretrained LM**, _Zhou et al._, NeurIPS 2023 Spotlight. \\[[paper](https://arxiv.org/abs/2302.11939)\\]\\[[code](https://github.com/DAMO-DI-ML/NeurIPS2023-One-Fits-All)\\]\\[[AI-for-Time-Series-Papers-Tutorials-Surveys](https://github.com/DAMO-DI-ML/AI-for-Time-Series-Papers-Tutorials-Surveys)\\]\\[[CALF](https://github.com/Hank0626/CALF)\\]\n- **Large Language Models Are Zero-Shot Time Series Forecasters**, _Gruver et al._, NeurIPS 2023. \\[[paper](https://arxiv.org/abs/2310.07820)\\]\\[[code](https://github.com/ngruver/llmtime)\\]\n- **Lag-Llama: Towards Foundation Models for Time Series Forecasting**, _Rasul et al._, arxiv 2023. \\[[paper](https://arxiv.org/abs/2310.08278)\\]\\[[code](https://github.com/time-series-foundation-models/lag-llama)\\]\n- TimesFM: **A decoder-only foundation model for time-series forecasting**, _Das et al._, ICML 2024. \\[[paper](https://arxiv.org/abs/2310.10688)\\]\\[[code](https://github.com/google-research/timesfm)\\]\n- **TimeGPT-1**, _Garza et al._, arxiv 2023. \\[[paper](https://arxiv.org/abs/2310.03589)\\]\\[[nixtla](https://github.com/Nixtla/nixtla)\\]\\[[sulie](https://github.com/wearesulie/sulie)\\]\n- **Time-LLM: Time Series Forecasting by Reprogramming Large Language Models**, _Jin et al._, ICLR 2024. \\[[paper](https://arxiv.org/abs/2310.01728)\\]\\[[code](https://github.com/KimMeen/Time-LLM)\\]\n- **AutoTimes: Autoregressive Time Series Forecasters via Large Language Models**, _Liu et al._, NeurIPS 2024. \\[[paper](https://arxiv.org/abs/2402.02370)\\]\\[[code](https://github.com/thuml/AutoTimes)\\]\n- **Timer: Generative Pre-trained Transformers Are Large Time Series Models**, _Liu et al._, ICML 2024. \\[[paper](https://arxiv.org/abs/2402.02368)\\]\\[[code](https://github.com/thuml/Large-Time-Series-Model)\\]\\[[Unified Time Series Dataset](https://huggingface.co/datasets/thuml/UTSD)\\]\\[[website](https://thuml.github.io/timer)\\]\\[[slides](https://cloud.tsinghua.edu.cn/f/b766629dbc584a4e8563/)\\]\n- **Timer-XL: Long-Context Transformers for Unified Time Series Forecasting**, _Liu et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2410.04803)\\]\\[[code](https://github.com/thuml/Timer-XL)\\]\\[[slides](https://cloud.tsinghua.edu.cn/f/2d4b660fc05148dc8f30/)\\]\n- **TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling**, _Dong et al._, ICML2024. \\[[paper](https://arxiv.org/abs/2402.02475)\\]\\[[code](https://github.com/thuml/TimeSiam)\\]\\[[slides](https://cloud.tsinghua.edu.cn/f/99ab4b2aec8b4614b7b4/)\\]\n- **Sundial: A Family of Highly Capable Time Series Foundation Models**, _Liu et al._, ICML 2025 Oral. \\[[paper](https://arxiv.org/abs/2502.00816)\\]\\[[code](https://github.com/thuml/Sundial)\\]\n- **MOMENT: A Family of Open Time-series Foundation Models**, _Goswami et al._, ICML 2024. \\[[paper](https://arxiv.org/abs/2402.03885)\\]\\[[code](https://github.com/moment-timeseries-foundation-model/moment)\\]\n- **Unified Training of Universal Time Series Forecasting Transformers**, _Woo et al._, ICML 2024. \\[[paper](https://arxiv.org/abs/2402.02592)\\]\\[[code](https://github.com/SalesforceAIResearch/uni2ts)\\]\n- **Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning**, _Bian et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2402.04852)\\]\n- **UNITS: A Unified Multi-Task Time Series Model**, _Gao et al._, NeurIPS 2024. \\[[paper](https://arxiv.org/abs/2403.00131)\\]\\[[code](https://github.com/mims-harvard/UniTS)\\]\n- **Chronos: Learning the Language of Time Series**, _Ansari et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2403.07815)\\]\\[[code](https://github.com/amazon-science/chronos-forecasting)\\]\n- **ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables**, _Arango et al._, arxiv 2025. \\[[paper](https://arxiv.org/abs/2503.12107)\\]\\[[code](https://github.com/amazon-science/chronos-forecasting/tree/chronosx)\\]\n- **Large language models can be zero-shot anomaly detectors for time series**, _Alnegheimish et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2405.14755)\\]\n- **Foundation Models for Time Series Analysis: A Tutorial and Survey**, _Liang et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2403.14735)\\]\\[[granite-tsfm](https://github.com/ibm-granite/granite-tsfm)\\]\n- **Are Language Models Actually Useful for Time Series Forecasting?**, _Tan et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2406.16964)\\]\\[[code](https://github.com/BennyTMT/TS_Models)\\]\n- **LETS-C: Leveraging Language Embedding for Time Series Classification**, _Kaur et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2407.06533)\\]\n- **Towards Neural Scaling Laws for Time Series Foundation Models**, _Yao et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2410.12360)\\]\n- **VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters**, _Chen et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2408.17253)\\]\\[[code](https://github.com/Keytoyze/VisionTS)\\]\n- **Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts**, _Shi et al._, ICLR 2025. \\[[paper](https://arxiv.org/abs/2409.16040)\\]\\[[code](https://github.com/Time-MoE/Time-MoE)\\]\\[[Moirai-MoE](https://arxiv.org/abs/2410.10469)\\]\n- **ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning**, _Xie et al._, VLDB 2025. \\[[paper](https://arxiv.org/abs/2412.03104)\\]\\[[code](https://github.com/NetManAIOps/ChatTS)\\]\n- **AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting**, _Benechehab et al._, arxiv 2025. \\[[paper](https://arxiv.org/abs/2502.10235)\\]\\[[code](https://github.com/abenechehab/AdaPTS)\\]\n- **TimesBERT: A BERT-Style Foundation Model for Time Series Understanding**, _Zhang et al._, arxiv 2025. \\[[paper](https://arxiv.org/abs/2502.21245)\\]\n- **This Time is Different: An Observability Perspective on Time Series Foundation Models**, _Cohen et al._, arxiv 2025. \\[[paper](https://arxiv.org/abs/2505.14766)\\]\\[[code](https://github.com/DataDog/toto)\\]\n- **Time-R1: Towards Comprehensive Temporal Reasoning in LLMs**, _Liu et al._, arxiv 2025. \\[[paper](https://arxiv.org/abs/2505.13508)\\]\\[[code](https://github.com/ulab-uiuc/Time-R1)\\]\\[[Position](https://arxiv.org/abs/2502.01477)\\]\n- **MIRA: Medical Time Series Foundation Model for Real-World Health Data**, _Li et al._, arxiv 2025. \\[[paper](https://arxiv.org/abs/2506.07584)\\]\\[[code](https://github.com/microsoft/MIRA)\\]\n- **Harnessing Vision-Language Models for Time Series Anomaly Detection**, _He et al._, AAAI 2026 Oral. \\[[paper](https://arxiv.org/abs/2506.06836)\\]\\[[code](https://github.com/ZLHe0/VLM4TS)\\]\n- **LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence**, _LimiX Team_, arxiv 2025. \\[[paper](https://arxiv.org/abs/2509.03505)\\]\\[[code](https://github.com/limix-ldm-ai/LimiX)\\]\n\n---\n## Diffusion Model\n- **Diffusion-TS: Interpretable Diffusion for General Time Series Generation**, _Yuan and Qiao_, ICLR 2024. \\[[paper](https://arxiv.org/abs/2403.01742)\\]\\[[code](https://github.com/Y-debug-sys/Diffusion-TS)\\]\n- **A Survey on Diffusion Models for Time Series and Spatio-Temporal Data**, _Yang et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2404.18886)\\]\\[[code](https://github.com/yyysjz1997/Awesome-TimeSeries-SpatioTemporal-Diffusion-Model)\\]\n- **TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model**, _Cao et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2409.02322)\\]\n- **TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation**, _Wang et al._, ICML 2025. \\[[paper](https://arxiv.org/abs/2410.05711)\\]\\[[code](https://github.com/Melmaphother/TimeDART)\\]\n- **UTSD: Unified Time Series Diffusion Model**, _Ma et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2412.03068)\\]\n- **Auto-Regressive Moving Diffusion Models for Time Series Forecasting**, _Gao et al._, AAAI 2025. \\[[paper](https://arxiv.org/abs/2412.09328)\\]\\[[code](https://github.com/daxin007/ARMD)\\]\n\n---\n\n## Benchmark and Dataset\n- **TSPP: A Unified Benchmarking Tool for Time-series Forecasting**, _Bączek et al._, arxiv 2023. \\[[paper](https://arxiv.org/abs/2312.17100)\\]\\[[code](https://github.com/NVIDIA/DeepLearningExamples/tree/master/Tools/PyTorch/TimeSeriesPredictionPlatform)\\]\n- **TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods**, _Qiu et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2403.20150)\\]\\[[code](https://github.com/decisionintelligence/TFB)\\]\n- **A Survey of Generative Techniques for Spatial-Temporal Data Mining**, _Zhang et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2405.09592)\\]\n- **Time-MMD: A New Multi-Domain Multimodal Dataset for Time Series Analysis**, _Liu et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2406.08627)\\]\\[[code](https://github.com/AdityaLab/Time-MMD)\\]\\[[MM-TSFlib](https://github.com/AdityaLab/MM-TSFlib)\\]\n- **GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation**, _Aksu et al._, arxiv 2024. \\[[paper](https://arxiv.org/abs/2410.10393)\\]\\[[code](https://github.com/SalesforceAIResearch/gift-eval)\\]\n- **FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting**, _Hu et al._, arxiv 2025. \\[[paper](https://arxiv.org/abs/2502.18834)\\]\\[[code](https://github.com/TongjiFinLab/FinTSB)\\]\n- **It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks**, _Qiao et al._, arxiv 2026. \\[[paper](https://arxiv.org/abs/2602.12147)\\]\n  \n- \\[[multivariate-time-series-data](https://github.com/laiguokun/multivariate-time-series-data)\\]\\[[ETDataset](https://github.com/zhouhaoyi/ETDataset)\\]\\[[Awesome-TimeSeries-SpatioTemporal-Diffusion-Model](https://github.com/yyysjz1997/Awesome-TimeSeries-SpatioTemporal-Diffusion-Model)\\]\\[[investment_data](https://github.com/chenditc/investment_data)\\]\n\n---\n\n## Repositories\n\n- \\[[Time-Series-Library](https://github.com/thuml/Time-Series-Library)\\]\n- \\[[time-series-transformers-review](https://github.com/qingsongedu/time-series-transformers-review)\\]\\[[awesome-AI-for-time-series-papers](https://github.com/qingsongedu/awesome-AI-for-time-series-papers)\\]\\[[Awesome-TimeSeries-SpatioTemporal-LM-LLM](https://github.com/qingsongedu/Awesome-TimeSeries-SpatioTemporal-LM-LLM)\\]\\[[TSFpaper](https://github.com/ddz16/TSFpaper)\\]\\[[deep-learning-time-series](https://github.com/Alro10/deep-learning-time-series)\\]\\[[LLMs4TS](https://github.com/wpf535236337/LLMs4TS)\\]\\[[awesome-time-series-papers](https://github.com/hushuguo/awesome-time-series-papers)\\]\\[[Awesome Time Series Forecasting Papers and Codes](https://github.com/TongjiFinLab/awesome-time-series-forecasting)\\]\\[[awesome-time-series-papers](https://github.com/TSCenter/awesome-time-series-papers)\\]\n- \\[[statsforecast](https://github.com/Nixtla/statsforecast)\\]\\[[neuralforecast](https://github.com/Nixtla/neuralforecast)\\]\\[[gluonts](https://github.com/awslabs/gluonts)\\]\\[[Merlion](https://github.com/salesforce/Merlion)\\]\\[[pytorch-forecasting](https://github.com/jdb78/pytorch-forecasting)\\]\\[[tsai](https://github.com/timeseriesAI/tsai)\\]\\[[pytorch-transformer-ts](https://github.com/kashif/pytorch-transformer-ts)\\]\\[[flow-forecast](https://github.com/AIStream-Peelout/flow-forecast)\\]\\[[pytorch-ts](https://github.com/zalandoresearch/pytorch-ts)\\]\n- \\[[AIAlpha](https://github.com/VivekPa/AIAlpha)\\]\n- \\[[prophet](https://github.com/facebook/prophet)\\]\\[[Kats](https://github.com/facebookresearch/Kats)\\]\\[[tsfresh](https://github.com/blue-yonder/tsfresh)\\]\\[[sktime](https://github.com/sktime/sktime)\\]\\[[darts](https://github.com/unit8co/darts)\\]\\[[tslearn](https://github.com/tslearn-team/tslearn)\\]\\[[pyflux](https://github.com/RJT1990/pyflux)\\]\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsongqiang321%2Ftime-series-papers","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsongqiang321%2Ftime-series-papers","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsongqiang321%2Ftime-series-papers/lists"}