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 5 / 11 页

  1. ICLR 2026Topological Anomaly Quantification for Semi-supervised Graph Anomaly Detection
  2. ICLR 2026Towards Generalizable PDE Dynamics Forecasting via Physics-Guided Invariant Learning
  3. ICLR 2026Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interaction
  4. ICLR 2026Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness
  5. ICLR 2026Transformers Don’t Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and Implications for Mechanistic Interpretability
  6. ICLR 2026TreeGrad-Ranker: Feature Ranking via $O(L)$-Time Gradients for Decision Trees
  7. ICLR 2026TrimR: Verifier-based Training-Free Thinking Trimming for Efficient Test-Time Scaling
  8. ICLR 2026TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series Analysis
  9. ICLR 2026Understanding the Implicit Biases of Design Choices for Time Series Foundation Models
  10. ICLR 2026UNDERSTANDING TRANSFORMERS FOR TIME SEIRES FORECASTING: A CASE STUDY ON MOIRAI
  11. ICLR 2026Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility
  12. ICLR 2026UniCA: Unified Covariate Adaptation for Time Series Foundation Model
  13. ICLR 2026Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecasting
  14. ICLR 2026Unmasking Backdoors: An Explainable Defense via Gradient-Attention Anomaly Scoring for Pre-trained Language Models
  15. ICLR 2026Weight-Space Linear Recurrent Neural Networks
  16. ICLR 2026When and Where to Reset Matters for Long-Term Test-Time Adaptation
  17. ICLR 2026When Foundation Models are One-Liners: Limitations and Future Directions for Time Series Anomaly Detection
  18. ICLR 2026When to Retrain after Drift: A Data-Only Test of Post-Drift Data Size Sufficiency
  19. ICLR 2026xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity
  20. ICLR 2026Zero-shot Forecasting by Simulation Alone
  21. ICLR 2025A deep inverse-mapping model for a flapping robotic wing
  22. ICLR 2025A Riemannian Framework for Learning Reduced-order Lagrangian Dynamics
  23. ICLR 2025Adaptive Retention & Correction: Test-Time Training for Continual Learning
  24. ICLR 2025Adversarially Robust Anomaly Detection through Spurious Negative Pair Mitigation
  25. ICLR 2025Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems
  26. ICLR 2025Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series
  27. ICLR 2025AnoLLM: Large Language Models for Tabular Anomaly Detection
  28. ICLR 2025AutoUAD: Hyper-parameter Optimization for Unsupervised Anomaly Detection
  29. ICLR 2025Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations
  30. ICLR 2025Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
  31. ICLR 2025Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling
  32. ICLR 2025Can LLMs Understand Time Series Anomalies?
  33. ICLR 2025CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching
  34. ICLR 2025CausalRivers - Scaling up benchmarking of causal discovery for real-world time-series
  35. ICLR 2025Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player Games
  36. ICLR 2025COME: Test-time Adaption by Conservatively Minimizing Entropy
  37. ICLR 2025Compositional simulation-based inference for time series
  38. ICLR 2025Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models
  39. ICLR 2025CoMRes: Semi-Supervised Time Series Forecasting Utilizing Consensus Promotion of Multi-Resolution
  40. ICLR 2025Context Steering: Controllable Personalization at Inference Time
  41. ICLR 2025Context-Alignment: Activating and Enhancing LLMs Capabilities in Time Series
  42. ICLR 2025Continual Slow-and-Fast Adaptation of Latent Neural Dynamics (CoSFan): Meta-Learning What-How & When to Adapt
  43. ICLR 2025Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
  44. ICLR 2025Controlling Space and Time with Diffusion Models
  45. ICLR 2025Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis
  46. ICLR 2025Differentially Private Federated Learning with Time-Adaptive Privacy Spending
  47. ICLR 2025DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector
  48. ICLR 2025Diffusion Transformers for Tabular Data Time Series Generation
  49. ICLR 2025Diffusion-based Decoupled Deterministic and Uncertain Framework for Probabilistic Multivariate Time Series Forecasting
  50. ICLR 2025DRL: Decomposed Representation Learning for Tabular Anomaly Detection

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