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 5 / 9 页

  1. ICML 2024ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection
  2. ICML 2024Explain Temporal Black-Box Models via Functional Decomposition
  3. ICML 2024Extending Test-Time Augmentation with Metamorphic Relations for Combinatorial Problems
  4. ICML 2024Finite Time Logarithmic Regret Bounds for Self-Tuning Regulation
  5. ICML 2024Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning
  6. ICML 2024Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning
  7. ICML 2024Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time Guarantees
  8. ICML 2024Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling
  9. ICML 2024Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting
  10. ICML 2024Hierarchical Novelty Detection via Fine-Grained Evidence Allocation
  11. ICML 2024Incremental Topological Ordering and Cycle Detection with Predictions
  12. ICML 2024Infinite-Horizon Distributionally Robust Regret-Optimal Control
  13. ICML 2024InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization
  14. ICML 2024Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach
  15. ICML 2024Jacobian Regularizer-based Neural Granger Causality
  16. ICML 2024Layerwise Change of Knowledge in Neural Networks
  17. ICML 2024Learning Causal Relations from Subsampled Time Series with Two Time-Slices
  18. ICML 2024Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding
  19. ICML 2024Learning Optimal Projection for Forecast Reconciliation of Hierarchical Time Series
  20. ICML 2024Learning with Adaptive Resource Allocation
  21. ICML 2024Log Neural Controlled Differential Equations: The Lie Brackets Make A Difference
  22. ICML 2024Long Range Propagation on Continuous-Time Dynamic Graphs
  23. ICML 2024Loss Shaping Constraints for Long-Term Time Series Forecasting
  24. ICML 2024Matroid Semi-Bandits in Sublinear Time
  25. ICML 2024Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective
  26. ICML 2024MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series
  27. ICML 2024MOMENT: A Family of Open Time-series Foundation Models
  28. ICML 2024Multi-Patch Prediction: Adapting Language Models for Time Series Representation Learning
  29. ICML 2024Near-Linear Time Approximation Algorithms for k-means with Outliers
  30. ICML 2024Network Tight Community Detection
  31. ICML 2024Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural Networks
  32. ICML 2024Non-parametric Online Change Point Detection on Riemannian Manifolds
  33. ICML 2024On the Identifiability of Switching Dynamical Systems
  34. ICML 2024Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs
  35. ICML 2024Optimal Batched Linear Bandits
  36. ICML 2024PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space Models
  37. ICML 2024Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?
  38. ICML 2024Position: What Can Large Language Models Tell Us about Time Series Analysis
  39. ICML 2024Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes
  40. ICML 2024Probabilistic Time Series Modeling with Decomposable Denoising Diffusion Model
  41. ICML 2024Projection-Free Online Convex Optimization with Time-Varying Constraints
  42. ICML 2024ReconBoost: Boosting Can Achieve Modality Reconcilement
  43. ICML 2024Replicable Learning of Large-Margin Halfspaces
  44. ICML 2024Reservoir Computing for Short High-Dimensional Time Series: an Application to SARS-CoV-2 Hospitalization Forecast
  45. ICML 2024Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling
  46. ICML 2024Run-Time Task Composition with Safety Semantics
  47. ICML 2024SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention
  48. ICML 2024Sampling in Unit Time with Kernel Fisher-Rao Flow
  49. ICML 2024SiBBlInGS: Similarity-driven Building-Block Inference using Graphs across States
  50. ICML 2024SIN: Selective and Interpretable Normalization for Long-Term 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