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 506 篇，第 6 / 11 页

  1. ICLR 2025DyCAST: Learning Dynamic Causal Structure from Time Series
  2. ICLR 2025Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models
  3. ICLR 2025Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement
  4. ICLR 2025Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions
  5. ICLR 2025Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
  6. ICLR 2025Efficiently Parameterized Neural Metriplectic Systems
  7. ICLR 2025Error-quantified Conformal Inference for Time Series
  8. ICLR 2025Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting
  9. ICLR 2025FACTS: A Factored State-Space Framework for World Modelling
  10. ICLR 2025Fast and Slow Streams for Online Time Series Forecasting Without Information Leakage
  11. ICLR 2025Federated Granger Causality Learning For Interdependent Clients With State Space Representation
  12. ICLR 2025Feedback Favors the Generalization of Neural ODEs
  13. ICLR 2025Filtered not Mixed: Filtering-Based Online Gating for Mixture of Large Language Models
  14. ICLR 2025Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond
  15. ICLR 2025Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
  16. ICLR 2025FreDF: Learning to Forecast in the Frequency Domain
  17. ICLR 2025From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics
  18. ICLR 2025Going Beyond Static: Understanding Shifts with Time-Series Attribution
  19. ICLR 2025HR-Extreme: A High-Resolution Dataset for Extreme Weather Forecasting
  20. ICLR 2025Identifying latent state transitions in non-linear dynamical systems
  21. ICLR 2025In-context Time Series Predictor
  22. ICLR 2025InstaTrain: Adaptive Training via Ultra-Fast Natural Annealing within Dynamical Systems
  23. ICLR 2025Intelligence at the Edge of Chaos
  24. ICLR 2025Investigating Pattern Neurons in Urban Time Series Forecasting
  25. ICLR 2025Kernel-based Optimally Weighted Conformal Time-Series Prediction
  26. ICLR 2025KooNPro: A Variance-Aware Koopman Probabilistic Model Enhanced by Neural Process for Time Series Forecasting
  27. ICLR 2025Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation Data
  28. ICLR 2025Learn hybrid prototypes for multivariate time series anomaly detection
  29. ICLR 2025Learning Chaos In A Linear Way
  30. ICLR 2025Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data
  31. ICLR 2025Learning Successor Features with Distributed Hebbian Temporal Memory
  32. ICLR 2025Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio Test
  33. ICLR 2025Learning under Temporal Label Noise
  34. ICLR 2025Learning vector fields of differential equations on manifolds with geometrically constrained operator-valued kernels
  35. ICLR 2025LevAttention: Time, Space and Streaming Efficient Algorithm for Heavy Attentions
  36. ICLR 2025Locally Connected Echo State Networks for Time Series Forecasting
  37. ICLR 2025Long-Context Linear System Identification
  38. ICLR 2025Long-time asymptotics of noisy SVGD outside the population limit
  39. ICLR 2025MamKO: Mamba-based Koopman operator for modeling and predictive control
  40. ICLR 2025Mask in the Mirror: Implicit Sparsification
  41. ICLR 2025Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling
  42. ICLR 2025Model-agnostic meta-learners for estimating heterogeneous treatment effects over time
  43. ICLR 2025Modeling Complex System Dynamics with Flow Matching Across Time and Conditions
  44. ICLR 2025MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection
  45. ICLR 2025MuHBoost: Multi-Label Boosting For Practical Longitudinal Human Behavior Modeling
  46. ICLR 2025Multi-Label Test-Time Adaptation with Bound Entropy Minimization
  47. ICLR 2025Multi-Resolution Decomposable Diffusion Model for Non-Stationary Time Series Anomaly Detection
  48. ICLR 2025Neural Context Flows for Meta-Learning of Dynamical Systems
  49. ICLR 2025Neural Functions for Learning Periodic Signal
  50. ICLR 2025Node-Time Conditional Prompt Learning in Dynamic Graphs

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