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 2,156 篇，第 20 / 44 页

  1. ICLR 2025A Riemannian Framework for Learning Reduced-order Lagrangian Dynamics
  2. ICLR 2025Adaptive Retention & Correction: Test-Time Training for Continual Learning
  3. ICLR 2025Adversarially Robust Anomaly Detection through Spurious Negative Pair Mitigation
  4. ICLR 2025Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems
  5. ICLR 2025Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series
  6. ICLR 2025AnoLLM: Large Language Models for Tabular Anomaly Detection
  7. ICLR 2025AutoUAD: Hyper-parameter Optimization for Unsupervised Anomaly Detection
  8. ICLR 2025Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations
  9. ICLR 2025Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
  10. ICLR 2025Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling
  11. ICLR 2025Can LLMs Understand Time Series Anomalies?
  12. ICLR 2025CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching
  13. ICLR 2025CausalRivers - Scaling up benchmarking of causal discovery for real-world time-series
  14. ICLR 2025Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player Games
  15. ICLR 2025COME: Test-time Adaption by Conservatively Minimizing Entropy
  16. ICLR 2025Compositional simulation-based inference for time series
  17. ICLR 2025Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models
  18. ICLR 2025CoMRes: Semi-Supervised Time Series Forecasting Utilizing Consensus Promotion of Multi-Resolution
  19. ICLR 2025Context Steering: Controllable Personalization at Inference Time
  20. ICLR 2025Context-Alignment: Activating and Enhancing LLMs Capabilities in Time Series
  21. ICLR 2025Continual Slow-and-Fast Adaptation of Latent Neural Dynamics (CoSFan): Meta-Learning What-How & When to Adapt
  22. ICLR 2025Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
  23. ICLR 2025Controlling Space and Time with Diffusion Models
  24. ICLR 2025Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis
  25. ICLR 2025Differentially Private Federated Learning with Time-Adaptive Privacy Spending
  26. ICLR 2025DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector
  27. ICLR 2025Diffusion Transformers for Tabular Data Time Series Generation
  28. ICLR 2025Diffusion-based Decoupled Deterministic and Uncertain Framework for Probabilistic Multivariate Time Series Forecasting
  29. ICLR 2025DRL: Decomposed Representation Learning for Tabular Anomaly Detection
  30. ICLR 2025DyCAST: Learning Dynamic Causal Structure from Time Series
  31. ICLR 2025Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models
  32. ICLR 2025Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement
  33. ICLR 2025Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions
  34. ICLR 2025Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
  35. ICLR 2025Efficiently Parameterized Neural Metriplectic Systems
  36. ICLR 2025Error-quantified Conformal Inference for Time Series
  37. ICLR 2025Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting
  38. ICLR 2025FACTS: A Factored State-Space Framework for World Modelling
  39. ICLR 2025Fast and Slow Streams for Online Time Series Forecasting Without Information Leakage
  40. ICLR 2025Federated Granger Causality Learning For Interdependent Clients With State Space Representation
  41. ICLR 2025Feedback Favors the Generalization of Neural ODEs
  42. ICLR 2025Filtered not Mixed: Filtering-Based Online Gating for Mixture of Large Language Models
  43. ICLR 2025Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond
  44. ICLR 2025Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
  45. ICLR 2025FreDF: Learning to Forecast in the Frequency Domain
  46. ICLR 2025From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics
  47. ICLR 2025Going Beyond Static: Understanding Shifts with Time-Series Attribution
  48. ICLR 2025HR-Extreme: A High-Resolution Dataset for Extreme Weather Forecasting
  49. ICLR 2025Identifying latent state transitions in non-linear dynamical systems
  50. ICLR 2025In-context Time Series Predictor

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