时间序列论文趋势 2023–2026

预测与异常检测

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,157 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

时间序列论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202391606259272
20241479511468424
202522113115974585
202629822026494876

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部时间序列论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 424 篇，第 6 / 9 页

  1. ICML 2024Sparsest Models Elude Pruning: An Exposé of Pruning’s Current Capabilities
  2. ICML 2024SparseTSF: Modeling Long-term Time Series Forecasting with *1k* Parameters
  3. ICML 2024Stealing part of a production language model
  4. ICML 2024Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction
  5. ICML 2024TENG: Time-Evolving Natural Gradient for Solving PDEs With Deep Neural Nets Toward Machine Precision
  6. ICML 2024Test-Time Degradation Adaptation for Open-Set Image Restoration
  7. ICML 2024Test-Time Model Adaptation with Only Forward Passes
  8. ICML 2024Test-Time Regret Minimization in Meta Reinforcement Learning
  9. ICML 2024The Fundamental Limits of Least-Privilege Learning
  10. ICML 2024Time Series Diffusion in the Frequency Domain
  11. ICML 2024Time Weaver: A Conditional Time Series Generation Model
  12. ICML 2024Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning
  13. ICML 2024TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning
  14. ICML 2024Timer: Generative Pre-trained Transformers Are Large Time Series Models
  15. ICML 2024TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling
  16. ICML 2024TimeX++: Learning Time-Series Explanations with Information Bottleneck
  17. ICML 2024Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles
  18. ICML 2024TSLANet: Rethinking Transformers for Time Series Representation Learning
  19. ICML 2024ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback
  20. ICML 2024Unified Training of Universal Time Series Forecasting Transformers
  21. ICML 2024UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis
  22. ICML 2024Vague Prototype-Oriented Diffusion Model for Multi-Class Anomaly Detection
  23. ICML 2024Variational Schrödinger Diffusion Models
  24. ICML 2024Vector Quantization Pretraining for EEG Time Series with Random Projection and Phase Alignment
  25. ICML 2024Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations
  26. ICML 2024What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement
  27. ICML 2024When and How Does In-Distribution Label Help Out-of-Distribution Detection?
  28. NeurIPS 2024A Continuous-time Stochastic Gradient Descent Method for Continuous Data
  29. NeurIPS 2024A Unified Recipe for Deriving (Time-Uniform) PAC-Bayes Bounds
  30. NeurIPS 2024Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series Classification
  31. NeurIPS 2024Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity
  32. NeurIPS 2024Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
  33. NeurIPS 2024Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
  34. NeurIPS 2024Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps
  35. NeurIPS 2024Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment
  36. NeurIPS 2024Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
  37. NeurIPS 2024ANT: Adaptive Noise Schedule for Time Series Diffusion Models
  38. NeurIPS 2024Are Language Models Actually Useful for Time Series Forecasting?
  39. NeurIPS 2024Are Self-Attentions Effective for Time Series Forecasting?
  40. NeurIPS 2024Asynchronous Perception Machine for Efficient Test Time Training
  41. NeurIPS 2024Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective
  42. NeurIPS 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
  43. NeurIPS 2024AverNet: All-in-one Video Restoration for Time-varying Unknown Degradations
  44. NeurIPS 2024BackTime: Backdoor Attacks on Multivariate Time Series Forecasting
  45. NeurIPS 2024Boosting Transferability and Discriminability for Time Series Domain Adaptation
  46. NeurIPS 2024Causal Contrastive Learning for Counterfactual Regression Over Time
  47. NeurIPS 2024Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models
  48. NeurIPS 2024ChronoEpilogi: Scalable Time Series Selection with Multiple Solutions
  49. NeurIPS 2024Con4m: Context-aware Consistency Learning Framework for Segmented Time Series Classification
  50. NeurIPS 2024CondTSF: One-line Plugin of Dataset Condensation for Time Series Forecasting

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查时间序列在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "time-series"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇时间序列论文？
共 2,157 篇，按年份分别是 2023 年 272 篇、2024 年 424 篇、2025 年 585 篇、2026 年 876 篇。
NeurIPS 2026 有多少篇时间序列论文？
NeurIPS 2026 有 298 篇时间序列论文，上一届是 221 篇。
ICLR 2026 有多少篇时间序列论文？
ICLR 2026 有 220 篇时间序列论文，上一届是 131 篇。
ICML 2026 有多少篇时间序列论文？
ICML 2026 有 264 篇时间序列论文，上一届是 159 篇。
CVPR 2026 有多少篇时间序列论文？
CVPR 2026 有 94 篇时间序列论文，上一届是 74 篇。
哪个会议的时间序列论文最多？
NeurIPS，2023–2026 年共 757 篇。

「图与结构化数据」下的其他主题