ICML 2026将在2026年7月6日—11日于韩国首尔Seoul, South Korea举行。本文总结了2026 ICML上有关时间序列time series相关论文。如有疏漏欢迎大家补充。注由于时间序列标题包含time series或time-series的论文高达125篇其中两篇可以算作时空除去还有123篇笔者将分为上中下3篇推文来总结此为第2篇本文主要涉及时间序列基础模型生成分类异常检测插补表示学习和分析等共计31篇。本文时间序列Topic时间序列基础模型TSFM生成分类异常检测插补表示学习和分析等。1. Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density2. Time-PEFT: Temporal and Multichannel Complexity-Based Fine-Tuning for Time-Series Foundation Models3. Universal Redundancies in Time Series Foundation Models4. Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning5. OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data6. HEARTS: Benchmarking LLM Reasoning on Health Time Series7. Position: Time-Series Foundation Models Require Explicit Domain-Level Benchmarks8. StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars9. Winformer: Transcending Pairwise Similarity for Time-series Generation10. ConTSG-Bench: A Unified Benchmark for Conditional Time Series Generation11. MN-Diff: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations12. TimeOmni-VL: Unified Models for Time Series Understanding and Generation13. CURE: Context-driven Diffusion with Progressive Expansion for Single Domain Generalization in Time Series Classification14. Time-CoT: Hierarchical Reasoning with Temporal Semantic Codes for Multivariate Time Series Classification15. MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification16. Mantis: Lightweight Foundation Model for Time Series Classification17. One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification18. Cluster-Aware Causal Mixer for Online Anomaly Detection in Multivariate Time Series19. COGNOS: Universal Enhancement for Time Series Anomaly Detection via Constrained Gaussian-Noise Optimization and Smoothing20. AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection21. IMPACT: Influence Modeling for Open-Set Time Series Anomaly Detection22. Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy23. Online Change Point Detection for Multivariate Inhomogeneous Poisson Processes Time Series24. TeamWork: Multivariate Time Series Anomaly Detection via Asymmetric Role-aware Channel Modeling25. HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation26. Rethinking Time-Series Imputation as Conditional Inference along Temporal Evolution27. Self-Supervised Dynamical System Representations for Physiological Time-Series28. One Batch Is Enough: A Unified Dataset Condensation Framework for General Time Series Analysis29. Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis30. TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis31. Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces1 Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density链接https://icml.cc/virtual/2026/poster/65289作者Jingru Fei ⋅ Kun Yi ⋅ Alex Wang ⋅ Qingsong Wen ⋅ Xiangxiang Zhu ⋅ Wei Fan关键词基础模型对齐融合频谱2 Time-PEFT: Temporal and Multichannel Complexity-Based Fine-Tuning for Time-Series Foundation Models链接https://icml.cc/virtual/2026/poster/61767作者Jihye Na ⋅ Patara Trirat ⋅ Chanyoung Park ⋅ Jae-Gil Lee关键词基础模型参数高效微调3 Universal Redundancies in Time Series Foundation Models链接https://icml.cc/virtual/2026/poster/65406arXivhttp://arxiv.org/abs/2602.01605v1代码https://github.com/abao1999/tsfm-lens作者Anthony Bao ⋅ Venkata Hasith Vattikuti ⋅ Jeffrey Lai ⋅ William Gilpin关键词基础模型可解释性压缩4 Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning链接https://icml.cc/virtual/2026/poster/64395arXivhttp://arxiv.org/abs/2602.07830v2作者Jiahui Zhou ⋅ Dan Li ⋅ Boxin Li ⋅ Xiao Zhang ⋅ Erli Meng ⋅ Lin Li ⋅ Zhuomin Chen ⋅ Jian Lou ⋅ See-Kiong Ng关键词时序推理5 OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data链接https://icml.cc/virtual/2026/poster/65261arXivhttp://arxiv.org/abs/2510.02410v3作者Patrick Langer ⋅ Thomas Kaar ⋅ Max Rosenblattl ⋅ Maxwell Xu ⋅ Winnie Chow ⋅ Martin Maritsch ⋅ Robert Jakob ⋅ Ning Wang ⋅ Juncheng Liu ⋅ Aradhana Verma ⋅ Brian Han ⋅ Daniel Kim ⋅ Henry Chubb ⋅ Scott Ceresnak ⋅ Aydin Zahedivash ⋅ Alexander Sandhu ⋅ Fatima Rodriguez ⋅ Daniel McDuff ⋅ Elgar Fleisch ⋅ Oliver Aalami ⋅ Filipe Barata ⋅ Paul Schmiedmayer关键词时序大模型医疗文本时序6 HEARTS: Benchmarking LLM Reasoning on Health Time Series链接https://icml.cc/virtual/2026/poster/61389arXivhttp://arxiv.org/abs/2603.06638v2代码https://github.com/yang-ai-lab/HEARTS作者Sirui Li ⋅ Shuhan Xiao ⋅ Mihir Joshi ⋅ Ahmed Metwally ⋅ Daniel McDuff ⋅ Wei Wang ⋅ Yuzhe Yang关键词benchmark健康时序时序推理7 Position: Time-Series Foundation Models Require Explicit Domain-Level Benchmarks链接https://icml.cc/virtual/2026/poster/67138作者Asif Bin Syed ⋅ Md Younus Ahamed ⋅ Azmine Toushik Wasi关键词领域级基准8 StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars链接https://icml.cc/virtual/2026/poster/63677arXivhttp://arxiv.org/abs/2510.06200v3代码https://github.com/skai-institute/StarEmbed作者Weijian Li ⋅ Hong-Yu Chen ⋅ Nabeel Rehemtulla ⋅ Ved Shah ⋅ Dongho Kim ⋅ Dennis Wu ⋅ Qinjie Lin ⋅ Adam Miller ⋅ Han Liu关键词benchmark恒星时间序列观测9 Winformer: Transcending Pairwise Similarity for Time-series Generation链接https://icml.cc/virtual/2026/poster/63196作者Haoyi Zhou ⋅ Xin Xue ⋅ Tianyu Chen ⋅ lanhao li ⋅ Lijun SUN ⋅ Jianxin Li关键词生成周期错位10 ConTSG-Bench: A Unified Benchmark for Conditional Time Series Generation链接https://icml.cc/virtual/2026/poster/64506arXivhttp://arxiv.org/abs/2603.04767v1代码https://github.com/seqml/ConTSG-Bench作者Shaocheng Lan ⋅ Shuqi Gu ⋅ Zhangzhi Xiong ⋅ Kan Ren关键词生成周期错位11 MN-Diff: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations链接https://icml.cc/virtual/2026/poster/61786作者Xu Zhang ⋅ Junwei Deng ⋅ Chang Xu ⋅ Hao Li ⋅ Jiang Bian关键词持续生成MoE不规则观察12 TimeOmni-VL: Unified Models for Time Series Understanding and Generation链接https://icml.cc/virtual/2026/poster/61019arXivhttp://arxiv.org/abs/2602.17149v1作者Tong Guan ⋅ SHENG PAN ⋅ Johan Barthelemy ⋅ Zhao Li ⋅ Yujun Cai ⋅ Cesare Alippi ⋅ Ming Jin ⋅ Shirui Pan关键词生成理解视觉模态13 CURE: Context-driven Diffusion with Progressive Expansion for Single Domain Generalization in Time Series Classification链接https://icml.cc/virtual/2026/poster/65631作者Yuhang Pei ⋅ Fanchun Meng ⋅ Wenrui Wu ⋅ Tao Ren ⋅ Yifan Wang ⋅ Wei Ju ⋅ Chao Zheng ⋅ Xiao Luo关键词分类扩散模型14 Time-CoT: Hierarchical Reasoning with Temporal Semantic Codes for Multivariate Time Series Classification链接https://icml.cc/virtual/2026/poster/62390作者Kun Zeng ⋅ Wu Binquan ⋅ Qianli Ma关键词分类时序思维链15 MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification链接https://icml.cc/virtual/2026/poster/61414作者Da Zhang ⋅ bingyu li ⋅ Zhiyuan Zhao ⋅ Hongyuan Zhang ⋅ Junyu Gao ⋅ Xuelong Li关键词医疗时序分类Mamba自适应图学习16 Mantis: Lightweight Foundation Model for Time Series Classification链接https://icml.cc/virtual/2026/poster/62438作者Vasilii Feofanov ⋅ Songkang Wen ⋅ Shifeng Xie ⋅ Simon Roschmann ⋅ Marius Alonso ⋅ Hongbo Guo ⋅ Romain Ilbert ⋅ Malik TIOMOKO ⋅ Quentin Bouniot ⋅ Zeynep Akata ⋅ Lujia Pan ⋅ Jianfeng Zhang ⋅ Ievgen Redko关键词分类轻量化基础模型17 One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification链接https://icml.cc/virtual/2026/poster/64769作者Mengzhou Gao ⋅ kaiwei wang ⋅ Pengfei Jiao关键词不规则时序分类神经流图结构18 Cluster-Aware Causal Mixer for Online Anomaly Detection in Multivariate Time Series链接https://icml.cc/virtual/2026/poster/64081arXivhttp://arxiv.org/abs/2506.00188v1作者Md Mahmuddun Nabi Murad ⋅ Yasin Yilmaz关键词在线异常检测19 COGNOS: Universal Enhancement for Time Series Anomaly Detection via Constrained Gaussian-Noise Optimization and Smoothing链接https://icml.cc/virtual/2026/poster/60841arXivhttp://arxiv.org/abs/2511.06894v2作者Wenlong Shang ⋅ Shihao Tian ⋅ Xutong Wan ⋅ Peng Chang关键词异常检测高斯噪声平滑20 AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection链接https://icml.cc/virtual/2026/poster/64969arXivhttp://arxiv.org/abs/2602.08868v1作者Junru Zhang ⋅ Lang Feng ⋅ Haoran Shi ⋅ Xu Guo ⋅ Han Yu ⋅ Yabo Dong ⋅ Duanqing Xu关键词异常检测多模态大模型21 IMPACT: Influence Modeling for Open-Set Time Series Anomaly Detection链接https://icml.cc/virtual/2026/poster/62939作者Xiaohui Zhou ⋅ Yijie Wang ⋅ Hongzuo Xu ⋅ Weixuan Liang ⋅ Xiaoli Li ⋅ Guansong Pang关键词开放集异常检测22 Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy链接https://icml.cc/virtual/2026/poster/60604arXivhttp://arxiv.org/abs/2509.21190v3作者Tian Lan ⋅ Hao Le ⋅ Jinbo Li ⋅ Wenjun He ⋅ Meng Wang ⋅ Chenghao Liu ⋅ Chen Zhang关键词异常检测零样本基础模型23 Online Change Point Detection for Multivariate Inhomogeneous Poisson Processes Time Series链接https://icml.cc/virtual/2026/poster/64844arXivhttp://arxiv.org/abs/2601.20192v1作者Xiaokai Luo ⋅ Haotian Xu ⋅ Carlos Misael Madrid Padilla ⋅ OSCAR HERNAN MADRID PADILLA关键词在线变点检测多元非齐次泊松点过程24 TeamWork: Multivariate Time Series Anomaly Detection via Asymmetric Role-aware Channel Modeling链接https://icml.cc/virtual/2026/poster/61471作者Shiyan Hu ⋅ Tengxue Zhang ⋅ Jianxin Jin ⋅ Xiangfei Qiu ⋅ Bin Yang ⋅ Chenjuan Guo关键词异常检测通道建模25 HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation链接https://icml.cc/virtual/2026/poster/65249arXivhttp://arxiv.org/abs/2605.02278v1代码https://github.com/milaogou/HELIX作者Fengming Zhang ⋅ Wenjie Du ⋅ Huan Zhang ⋅ Ke Yu ⋅ Shen Qu关键词插补跨维度同步混合编码26 Rethinking Time-Series Imputation as Conditional Inference along Temporal Evolution链接https://icml.cc/virtual/2026/poster/66294作者Yu Fan ⋅ Yang Yang ⋅ Yufan Guo ⋅ Huazhong Yang ⋅ pengjun wang关键词插补条件时序推理27 Self-Supervised Dynamical System Representations for Physiological Time-Series链接https://icml.cc/virtual/2026/poster/62877arXivhttp://arxiv.org/abs/2512.00239v1作者Yenho Chen ⋅ Maxwell Xu ⋅ James Rehg ⋅ Christopher Rozell关键词生理时序自监督28 One Batch Is Enough: A Unified Dataset Condensation Framework for General Time Series Analysis链接https://icml.cc/virtual/2026/poster/62269作者Wei Shao ⋅ Ziquan Fang ⋅ Zheqi Lu ⋅ Yongfeng Su ⋅ Yuzhu Wang ⋅ Yunjun Gao关键词时序分析数据集浓缩29 Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis链接https://icml.cc/virtual/2026/poster/65415作者Yisong Fu ⋅ Zezhi Shao ⋅ Chengqing Yu ⋅ Yujie Li ⋅ Yongjun Xu ⋅ Xueqi Cheng ⋅ Fei Wang关键词时序分析基础模型30 TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis链接https://icml.cc/virtual/2026/poster/61690arXivhttp://arxiv.org/abs/2510.06063v1代码https://github.com/Ali-maatouk/TelecomTS作者Austin Feng ⋅ Andreas Varvarigos ⋅ Ioannis Panitsas ⋅ Daniela Fernandez ⋅ Yuwei Guo ⋅ Jinbiao Wei ⋅ Chen ⋅ Ali Maatouk ⋅ Leandros Tassiulas ⋅ ZHITAO YING关键词多模态可观测性数据集通讯时序31 Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces链接https://icml.cc/virtual/2026/poster/63821arXivhttp://arxiv.org/abs/2602.19367v1作者Pratham Yashwante ⋅ Rose Yu关键词表示学习三模态时序视觉文本对齐