ICML 2026 | 时间序列预测(TSF)论文总结【LLM，时间序列基础模型，协变量，不规则时序，非平稳时序，稳健时序预测，不确定性量化等】

时空探索之旅

发布于 2026-05-11 14:38:22

5860

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上有关时间序列预测（time series forecasting）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，本文主要涉及时间序列预测（Time Seires Forecasting, TSF）的论文，涉及53篇。

时间序列预测Topic：LLM，时间序列基础模型，不规则时序，非平稳时序，稳健时间序列预测，不确定性量化等。

1. L-Drive: Beyond a Single Mapping—Latent Context Drives Time Series Forecasting2. ConFlux: Multivariate Time Series in Flux, One Unified Forecast in Confluence3. PESD-TSF: A Period-Aware and Explicit Structured Decomposition Framework for Long-Term Time Series Forecasting4. Parameter Decorrelation via Transition-Variance Alignment for Multivariate Time-series Forecasting5. It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks6. DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting7. Time-series forecasting through the lens of dynamics8. Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting9. Byte Pair Encoding for Efficient Time Series Forecasting10. TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting11. What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions12. Beyond Point Predictions: Manifold Expansion and Dual Alignment for Robust Time Series Distillation13. Channel Adapter for Time Series Foundation Models in Zero-Shot Multivariate Forecasting14. Beyond Extrapolation: Knowledge Utilization Paradigm with Bidirectional Inspiration for Time Series Forecasting15. Invariant Representation Learning for Source-Free Time Series Forecasting with LLM-Centric Proxy Denoising16. FIPN: Forward Self-Organizing Interpretable Polynomial Networks for Time Series Forecasting17. Anti-Aliasing Matters: A Dynamic Network for Time Series Forecasting18. DSENet: A Novel Dual-Stream Enhancement Network for Multi-Scale Non-Stationary Time Series Forecasting19. Crisp: A Spectral-Based Interaction Strategy for Multivariate Time Series Forecasting20. Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting21. KITE: Knowledge-Guided Probabilistic Modeling for Time Series Forecasting with Exogenous Variables22. TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction23. ReNF: Rethinking the Principles of Neural Long-Term Time Series Forecasters24. Reviving Error Correction in Modern Deep Time-Series Forecasting25. MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning26. Delving into Non-Exchangeability for Conformal Prediction in Graph-Structured Multivariate Time Series27. TSFAdv: Frequency-Guided Black-Box Adversarial Attacks on Time Series Forecasting28. Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasting29. Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting30. Ellipsoidal Time Series Forecasting31. Conditional Quantile Adjusted Conformal Prediction for Time Series32. CoGenCast: A Coupled Autoregressive–Flow Generative Framework for Time Series Forecasting33. StretchTime: Adaptive Time Series Forecasting via Symplectic Attention34. Robust Inter-Series Dependency Modeling for Time Series Forecasting via Information-Theoretic Alignment35. CombinationTS: A Modular Framework for Understanding Time-Series Forecasting Models36. See More, Forecast Better and Faster: Enhancing Time Series Foundation Models via Inference-Time Plug-and-Play Downsampling37. Taming the Recent-Data Bias: Towards Robust Time Series Forecasting with Global Context38. KineFlow: Kinematic Second-Order Flow Matching for Time-Series Forecasting39. From Observations to States: Latent Time Series Forecasting40. Baguan-TS: dual in-context learning model for time series forecasting with covariates41. Position: Current Benchmarking Hinders Real Progress in Deep Learning for Time Series Forecasting42. TimeMRA: LLM-Empowered Time Series Forecasting via Multi-Scale Retrieval-Augmented Representations43. Rethinking Multimodal Time-Series Forecasting Evaluation44. Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecasting45. DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables46. SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement47. TimeSeed: Effective Time Series Forecasting with Sparse Endogenous Variables48. Information Geometry Loss for Time Series Forecasting49. KUMA: A Novel Framework with Koopman Separation and Efficient Multilevel Extraction in Time Series Forecasting50. Revealing Scaling Behavior in Large-scale Time Series Models: Implications for More Efficient and Accurate Forecasting51. PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting52. Not All Frequencies Are Equal: Energy-Adaptive Diffusion for Time Series Forecasting53. MoRGEN: Mixture-of-Resolutions Generative Forecasting for Irregularly Sampled Medical Time-Series Data

点击文末阅读原文跳转笔者知乎链接（跳转论文链接更方便）

1 L-Drive: Beyond a Single Mapping—Latent Context Drives Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/64484

作者：Fan Zhang ⋅ Shijun Chen ⋅ Hua Wang

关键词：隐式上下文驱动，变化感知

2 ConFlux: Multivariate Time Series in Flux, One Unified Forecast in Confluence

链接：https://icml.cc/virtual/2026/poster/61370

作者：Shiyu Wang ⋅ Yuchen Fang ⋅ Juntong Ni ⋅ Ziyi Zhang ⋅ Baichuan Mo ⋅ Xinyue Zhong ⋅ Chengxin Wang ⋅ Zhou Ye ⋅ Yang Xiang

关键词：百川归海

3 PESD-TSF: A Period-Aware and Explicit Structured Decomposition Framework for Long-Term Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/65742

作者：Hua Wang ⋅ Xianhao jiao ⋅ Fan Zhang

关键词：周期感知，显式结构分解

4 Parameter Decorrelation via Transition-Variance Alignment for Multivariate Time-series Forecasting

链接：https://icml.cc/virtual/2026/poster/64647

作者：Ji-Eun Choi ⋅ Jae-Hong Lee ⋅ Joon Hyuk Chang

关键词：转移方差对齐，马尔科夫链

5 It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks

链接：https://icml.cc/virtual/2026/poster/66086

arXiv：http://arxiv.org/abs/2602.12147v3

代码：https://github.com/zqiao11/TIME

作者：Zhongzheng Qiao ⋅ SHENG PAN ⋅ Anni Wang ⋅ Viktoriya Zhukova ⋅ Yong Liu ⋅ Xudong Jiang ⋅ Qingsong Wen ⋅ Mingsheng Long ⋅ Ming Jin ⋅ Chenghao Liu

关键词：benchmark，基础模型

TIME: 突破时序基础模型评估瓶颈, 下一代任务驱动时序预测Benchmark

6 DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/66019

arXiv：http://arxiv.org/abs/2601.21726v1

作者： Siru Zhong ⋅ Yiqiu Liu ⋅ Zhiqing Cui ⋅ Zezhi Shao ⋅ Fei Wang ⋅ Qingsong Wen ⋅ Yuxuan Liang

关键词：频域，样本自适应

ICML 2026｜DropoutTS：从”学什么”到”学多少”的鲁棒时间序列预测

7 Time-series forecasting through the lens of dynamics

链接：https://icml.cc/virtual/2026/poster/64363

arXiv：http://arxiv.org/abs/2507.15774v2

作者：Alexis-Raja Brachet ⋅ Pierre-Yves Richard ⋅ Céline Hudelot

关键词：数据底层动态

8 Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting

链接：https://icml.cc/virtual/2026/poster/65039

arXiv：https://arxiv.org/abs/2406.14399

代码：https://github.com/taohan10200/WEATHER-5K

作者：Tao Han ⋅ Zhibin Wen ⋅ Zhenghao Chen ⋅ Dazhao Du ⋅ Song Guo ⋅ LEI BAI

关键词：天气预报，物理驱动的时序模型

9 Byte Pair Encoding for Efficient Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/64868

arXiv：http://arxiv.org/abs/2505.14411v3

作者： Leon Götz ⋅ Marcel Kollovieh ⋅ Stephan Günnemann ⋅ Leo Schwinn

关键词：token化，解码

10 TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/64726

作者：Quang Duc Nguyen ⋅ Siyuan Liang ⋅ Yiming Li ⋅ Fushuo Huo ⋅ Dacheng Tao

关键词：后门防御

11 What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions

链接：https://icml.cc/virtual/2026/poster/65690

作者：Shuqi Gu ⋅ Yongxiang Zhao ⋅ Baoyu Jing ⋅ Kan Ren

关键词：反事实，多模态

12 Beyond Point Predictions: Manifold Expansion and Dual Alignment for Robust Time Series Distillation

链接：https://icml.cc/virtual/2026/poster/65540

作者：Junyao Hong ⋅ Zesheng Lai ⋅ Xinyi Xiao ⋅ Suyang Zhou ⋅ Aodong Shen ⋅ Youyong Kong

关键词：知识蒸馏，双重对齐，流形扩展

13 Channel Adapter for Time Series Foundation Models in Zero-Shot Multivariate Forecasting

链接：https://icml.cc/virtual/2026/poster/64366

作者：Dongyuan Li ⋅ Renhe Jiang ⋅ Shun Zheng ⋅ Zheng Dong ⋅ Haotian Gao ⋅ Ying Zhang ⋅ Jiang Bian

关键词：通道自适应，零样本

14 Beyond Extrapolation: Knowledge Utilization Paradigm with Bidirectional Inspiration for Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/63442

作者：Liu Chong ⋅ Yingjie Zhou ⋅ Hao Li ⋅ Pengyang Wang ⋅ Qingsong Wen ⋅ Ce Zhu

关键词：知识利用，双向启发

15 Invariant Representation Learning for Source-Free Time Series Forecasting with LLM-Centric Proxy Denoising

链接：https://icml.cc/virtual/2026/poster/66175

作者：Kangjia Yan ⋅ Chenxi Liu ⋅ Hao Miao ⋅ Xinle Wu ⋅ Yan Zhao ⋅ Chenjuan Guo ⋅ Bin Yang

关键词：迁移学习，LLM

16 FIPN: Forward Self-Organizing Interpretable Polynomial Networks for Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/64118

作者：YiZhen Wang ⋅ Zheng Wang ⋅ EUN-HU KIM ⋅ Zunwei Fu

关键词：自组织，可解释，多项式

17 Anti-Aliasing Matters: A Dynamic Network for Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/62513

作者：Heng Zhou ⋅ Xin Sun ⋅ Chao Li

关键词：频谱混叠，动态网络

18 DSENet: A Novel Dual-Stream Enhancement Network for Multi-Scale Non-Stationary Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/62164

作者：Yuhan Wang ⋅ Yuanyuan Zou ⋅ Jie Cheng ⋅ Bin Dai ⋅ Jinhong Guo

关键词：多尺度，非平稳，医疗时序

19 Crisp: A Spectral-Based Interaction Strategy for Multivariate Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/63011

作者：Binwu Wang ⋅ Gaoyun Lin ⋅ Jiaming Ma ⋅ Qihe Huang ⋅ Zhengyang Zhou ⋅ Xu Wang ⋅ Pengkun Wang ⋅ Yang Wang

关键词：谱先验

20 Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/64886

arXiv：http://arxiv.org/abs/2509.23074v2

作者：Wanjin Feng ⋅ Yuan Yuan ⋅ Ding ⋅ Yong Li

关键词：线性利用率，可预测漂移

21 KITE: Knowledge-Guided Probabilistic Modeling for Time Series Forecasting with Exogenous Variables

链接：https://icml.cc/virtual/2026/poster/65231

作者：Hanyin Cheng ⋅ Jingrong Zhou ⋅ Yang Shu ⋅ Chenjuan Guo

关键词：协变量预测，不确定性量化

22 TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction

链接：https://icml.cc/virtual/2026/poster/61098

作者：Felix Parker ⋅ Nimeesha Chan ⋅ Chi Zhang ⋅ Kimia Ghobadi

关键词：LLM，时序理解

23 ReNF: Rethinking the Principles of Neural Long-Term Time Series Forecasters

链接：https://icml.cc/virtual/2026/poster/62639

作者：Yihang Lu ⋅ Xianwei Meng ⋅ Enhong Chen

关键词：神经预测模型，自回归

24 Reviving Error Correction in Modern Deep Time-Series Forecasting

链接：https://icml.cc/virtual/2026/poster/63134

作者：Minh Nguyen ⋅ Van Dai Do ⋅ Huu Nguyen ⋅ Dung Nguyen ⋅ Kien Do ⋅ Hung Le

关键词：误差校正机制

25 MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning

链接：https://icml.cc/virtual/2026/poster/64890

arXiv：http://arxiv.org/abs/2602.03164v1

代码：https://github.com/Xiaoyu-Tao/MemCast-TS

作者：Xiaoyu Tao ⋅ Mingyue Cheng ⋅ Ze Guo ⋅ Shuo Yu ⋅ Yaguo Liu ⋅ Qi Liu ⋅ Shijin Wang

关键词：记忆机制，推理

ztxtech：MemCast：基于经验记忆的时间序列预测新框架

26 Delving into Non-Exchangeability for Conformal Prediction in Graph-Structured Multivariate Time Series

链接：https://icml.cc/virtual/2026/poster/66198

arXiv：http://arxiv.org/abs/2605.04957v1

作者：Ruichao Guo ⋅ Xingyao Han ⋅ Wenshui Luo ⋅ Zhe Liu ⋅ Chen Gong ⋅ Hesheng Wang

关键词：共形预测，不确定性量化

27 TSFAdv: Frequency-Guided Black-Box Adversarial Attacks on Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/66215

作者：Qizhuo Han ⋅ Xiangrui Cai ⋅ Sihan Xu ⋅ Ying Zhang ⋅ Zheli Liu

关键词：黑盒对抗攻击

28 Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/61351

作者：Jinglin Li ⋅ Jun Tan ⋅ QI Fang ⋅ Ning Gui

关键词：非平稳时序，概率预测

29 Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/64808

作者：Jiawen Zhu ⋅ Shuhan Liu ⋅ Di Weng ⋅ Yingcai Wu

关键词：非平稳时序，MoE

30 Ellipsoidal Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/65519

arXiv：http://arxiv.org/abs/2505.17370v6

作者：Qilin Wang

关键词：谱结构，有效预测时长（EPT）

31 Conditional Quantile Adjusted Conformal Prediction for Time Series

链接：https://icml.cc/virtual/2026/poster/64983

作者：Cheng Yu ⋅ Zhoufan Zhu ⋅ Ke Zhu

关键词：条件分位数，共形预测

32 CoGenCast: A Coupled Autoregressive–Flow Generative Framework for Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/64629

arXiv：https://arxiv.org/abs/2602.03564

作者：Yaguo Liu ⋅ Mingyue Cheng ⋅ Daoyu Wang ⋅ Xiaoyu Tao ⋅ Qi Liu

关键词：自回归，流匹配

33 StretchTime: Adaptive Time Series Forecasting via Symplectic Attention

链接：https://icml.cc/virtual/2026/poster/66150

作者：Yubin Kim ⋅ Viresh Pati ⋅ Jevon Twitty ⋅ Vinh Pham ⋅ Shihao Yang ⋅ Jiecheng Lu

关键词：辛注意力，旋转位置编码

34 Robust Inter-Series Dependency Modeling for Time Series Forecasting via Information-Theoretic Alignment

链接：https://icml.cc/virtual/2026/poster/63281

作者：Wuqing Yu ⋅ Weichen Guo ⋅ Jian Zhou ⋅ Shuyu Luo ⋅ Jiacai Zhang

关键词：图 Transformer ，周期性

35 CombinationTS: A Modular Framework for Understanding Time-Series Forecasting Models

链接：https://icml.cc/virtual/2026/poster/65509

arXiv：http://arxiv.org/abs/2605.01231v1

作者：Xiaorui Wang ⋅ Fanda Fan ⋅ Chenxi Wang ⋅ Yuxuan Yang ⋅ Rui Tang ⋅ Kuoyu Gao ⋅ simiao pang ⋅ Yuanfeng Shang ⋅ Liu ⋅ Gao ⋅ Lei Wang ⋅ Jianfeng Zhan

关键词：模块化归因

36 See More, Forecast Better and Faster: Enhancing Time Series Foundation Models via Inference-Time Plug-and-Play Downsampling

链接：https://icml.cc/virtual/2026/poster/64120

作者：Longlong Xu ⋅ Zeyan Li ⋅ Xiao He ⋅ Zhaoyang Yu ⋅ Dazhong Wen ⋅ Mingze Sun ⋅ Changhua Pei ⋅ Dan Pei

关键词：时序基础模型，下采样，插件

37 Taming the Recent-Data Bias: Towards Robust Time Series Forecasting with Global Context

链接：https://icml.cc/virtual/2026/poster/62481

作者：Longlong Xu ⋅ Zeyan Li ⋅ Xiao He ⋅ Zhaoyang Yu ⋅ Changhua Pei ⋅ Zhe Xie ⋅ Zijun Dou ⋅ Tieying Zhang ⋅ Dan Pei

关键词：近期数据偏差，全局上下文

38 KineFlow: Kinematic Second-Order Flow Matching for Time-Series Forecasting

链接：https://icml.cc/virtual/2026/poster/66194

作者：Haiqi Jiang ⋅ Hui Xiong

关键词：流匹配，生成式，运动学

39 From Observations to States: Latent Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/61261

arXiv：http://arxiv.org/abs/2602.00297v1

代码：https://github.com/Muyiiiii/LatentTSF

作者：Jie Yang ⋅ Yifan Hu ⋅ Yuante Li ⋅ Kexin Zhang ⋅ Kaize Ding ⋅ Philip Yu

关键词：隐空间时间序列预测

40 Baguan-TS: dual in-context learning model for time series forecasting with covariates

链接：https://icml.cc/virtual/2026/poster/60703

arXiv：https://arxiv.org/abs/2603.17439

作者：Linxiao Yang ⋅ Xue Jiang ⋅ Gezheng Xu ⋅ Tian Zhou ⋅ Min Yang ⋅ Zhaoyang Zhu ⋅ Linyuan Geng ⋅ Zhipeng Zeng ⋅ Qiming Chen ⋅ Xinyue Gu ⋅ Rong Jin ⋅ Liang Sun

关键词：上下文学习，协变量

AI论文速读 | Baguan-TS：面向含协变量时间序列预测的序列原生上下文学习模型

41 Position: Current Benchmarking Hinders Real Progress in Deep Learning for Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/67106

arXiv：https://arxiv.org/abs/2512.22702

作者：Valentina Moretti ⋅ Andrea Cini ⋅ Ivan Marisca ⋅ Cesare Alippi

关键词：辅助预测模型卡片

AI论文速读 | 深度时序预测什么才是关键？四大设计维度拆解虚假进步，重塑评估标准

42 TimeMRA: LLM-Empowered Time Series Forecasting via Multi-Scale Retrieval-Augmented Representations

链接：https://icml.cc/virtual/2026/poster/62393

作者：Zongjiang Shang ⋅ Chengxi Jin ⋅ Binqing Wu ⋅ Dongliang Cui ⋅ Yue Yu ⋅ Haobang Sun ⋅ Chuanlin Xu ⋅ Ling Chen

关键词：LLM，RAG

43 Rethinking Multimodal Time-Series Forecasting Evaluation

链接：https://icml.cc/virtual/2026/poster/63015

作者：Haoxin Liu ⋅ Yichen Zhou ⋅ Rajat Sen ⋅ B. Aditya Prakash ⋅ Abhimanyu Das

关键词：多模态时序预测评估

44 Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/65148

arXiv：http://arxiv.org/abs/2602.00582v1

作者：Xiangfei Qiu ⋅ Kangjia Yan ⋅ Xvyuan Liu ⋅ Xingjian Wu ⋅ Jilin Hu

关键词：不规则时序，时频联合建模

45 DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables

链接：https://icml.cc/virtual/2026/poster/62103

arXiv：http://arxiv.org/abs/2509.14933v2

作者：Xiangfei Qiu ⋅ Yuhan Zhu ⋅ Zhengyu Li ⋅ Xingjian Wu ⋅ Bin Yang ⋅ Jilin Hu

关键词：协变量，未来可知/近似可知协变量

46 SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement

链接：https://icml.cc/virtual/2026/poster/61675

arXiv：http://arxiv.org/abs/2602.00589v1

作者：Xiangfei Qiu ⋅ Xvyuan Liu ⋅ Tianen Shen ⋅ Xingjian Wu ⋅ Hanyin Cheng ⋅ Bin Yang ⋅ Jilin Hu

关键词：稳健性，Patch增强与替换

科学最TOP：ICML26｜SEER：用MoE+可学习Patch替换，做鲁棒的时序预测

47 TimeSeed: Effective Time Series Forecasting with Sparse Endogenous Variables

链接：https://icml.cc/virtual/2026/poster/61541

作者：Zhaowang Wu ⋅ Kaixin Deng ⋅ Hua Yan

关键词：稀疏内生预测

48 Information Geometry Loss for Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/66595

作者：Jiayu Fang ⋅ Xuande Liu ⋅ Sangsha Fang ⋅ Zhen Tian ⋅ Hongwei Ma ⋅ Zhiqi Shao ⋅ Junbin Gao

关键词：信息几何损失，不确定性量化

49 KUMA: A Novel Framework with Koopman Separation and Efficient Multilevel Extraction in Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/64743

作者：Sijie Xiong ⋅ Cheng Tang ⋅ Atsushi Shimada

关键词：U 型多层注意力，库普曼

50 Revealing Scaling Behavior in Large-scale Time Series Models: Implications for More Efficient and Accurate Forecasting

链接：https://icml.cc/virtual/2026/poster/63243

作者：Xin Qiu ⋅ Junlong Tong ⋅ Yirong Sun ⋅ Yunpu Ma ⋅ Anhao Zhao

关键词：少层主导效应，LLM4TS，时序基础模型

51 PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/64838

作者：Yangyou Liu ⋅ Zezhi Shao ⋅ Xinyu Chen ⋅ Hu Chen ⋅ Fei Wang ⋅ Yuankai Wu

关键词：非平稳时序，相位

52 Not All Frequencies Are Equal: Energy-Adaptive Diffusion for Time Series Forecasting

链接：https://icml.cc/virtual/2026/poster/66318

作者：Zining Qin ⋅ Huiling qin ⋅ Chenhao Wang ⋅ Jianxiong Guo ⋅ Tian Wang ⋅ Weijia Jia

关键词：扩散模型，小波，能量模型

53 MoRGEN: Mixture-of-Resolutions Generative Forecasting for Irregularly Sampled Medical Time-Series Data

链接：https://icml.cc/virtual/2026/poster/64999

作者：Nassim Oufattole ⋅ Matthew McDermott ⋅ Collin Stultz

关键词：多分辨率混合生成模型，不规则时序

本文参与腾讯云自媒体同步曝光计划，分享自微信公众号。

原始发表：2026-05-10，如有侵权请联系 cloudcommunity@tencent.com 删除

基础

本文分享自时空探索之旅微信公众号，前往查看

如有侵权，请联系 cloudcommunity@tencent.com 删除。

本文参与腾讯云自媒体同步曝光计划，欢迎热爱写作的你一起参与！

登录后参与评论

0 条评论

热度