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 875 篇，第 6 / 18 页

  1. ICLR 2026SCRAPL: Scattering Transform with Random Paths for Machine Learning
  2. ICLR 2026SELF-HARMONY: LEARNING TO HARMONIZE SELF-SUPERVISION AND SELF-PLAY IN TEST-TIME REINFORCEMENT LEARNING
  3. ICLR 2026Semantic-Enhanced Time-Series Forecasting via Large Language Models
  4. ICLR 2026Shift-Tolerant Allocation via Black-Litterman Using Conditional Diffusion Estimates
  5. ICLR 2026SONATA: Synergistic Coreset Informed Adaptive Temporal Tensor Factorization
  6. ICLR 2026SRT: Super-Resolution for Time Series via Disentangled Rectified Flow
  7. ICLR 2026ST-HHOL: Spatio-Temporal Hierarchical Hypergraph Online Learning for Crime Prediction
  8. ICLR 2026Step-Aware Residual-Guided Diffusion for EEG Spatial Super-Resolution
  9. ICLR 2026Stochastic Optimal Control for Continuous-Time fMRI Representation Learning
  10. ICLR 2026STORM: Synergistic Cross-Scale Spatio-Temporal Modeling for Weather Forecasting
  11. ICLR 2026Strategic Scaling of Test-Time Compute: A Bandit Learning Approach
  12. ICLR 2026Structure Learning from Time-Series Data with Lag-Agnostic Structural Prior
  13. ICLR 2026Sublinear Time Quantum Algorithm for Attention Approximation
  14. ICLR 2026Subspace Kernel Learning on Tensor Sequences
  15. ICLR 2026SwiftTS: A Swift Selection Framework for Time Series Pre-trained Models via Multi-task Meta-Learning
  16. ICLR 2026T1: One-to-One Channel-Head Binding for Multivariate Time-Series Imputation
  17. ICLR 2026T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models
  18. ICLR 2026Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift
  19. ICLR 2026TAMMs: Change Understanding and Forecasting in Satellite Image Time Series with Temporal-Aware Multimodal Models
  20. ICLR 2026TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations
  21. ICLR 2026TEDM: Time Series Forecasting with Elucidated Diffusion Models
  22. ICLR 2026TEN-DM: Topology-Enhanced Diffusion Model for Spatio-Temporal Event Prediction
  23. ICLR 2026Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting
  24. ICLR 2026Test-Time Iterative Error Correction for Efficient Diffusion Models
  25. ICLR 2026Test-Time Optimization of 3D Point Cloud LLM via Manifold-Aware In-Context Guidance and Refinement
  26. ICLR 2026Test-Time Poisoned Sample Detection by Exploiting Shallow Malicious Matching in Backdoored CLIP
  27. ICLR 2026Test-Time Training Done Right
  28. ICLR 2026Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimality
  29. ICLR 2026The Coverage Principle: How Pre-Training Enables Post-Training
  30. ICLR 2026The Curious Case of In-Training Compression of State Space Models
  31. ICLR 2026The Diffusion Duality, Chapter II: $\Psi$-Samplers and Efficient Curriculum
  32. ICLR 2026The Forecast After the Forecast: A Post-Processing Shift in Time Series
  33. ICLR 2026The Markovian Thinker
  34. ICLR 2026Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time
  35. ICLR 2026Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models
  36. ICLR 2026Time Optimal Execution of Action Chunk Policies Beyond Demonstration Speed
  37. ICLR 2026Time-Gated Multi-Scale Flow Matching for Time-Series Imputation
  38. ICLR 2026TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models
  39. ICLR 2026TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness
  40. ICLR 2026TimeSeg: An Information-Theoretic Segment-Wise Explainer for Time-Series Predictions
  41. ICLR 2026TIMESLIVER : SYMBOLIC-LINEAR DECOMPOSITION FOR EXPLAINABLE TIME SERIES CLASSIFICATION
  42. ICLR 2026TNT: Improving Chunkwise Training for Test-Time Memorization
  43. ICLR 2026Tokenizing Single-Channel EEG with Time-Frequency Motif Learning
  44. ICLR 2026Topological Anomaly Quantification for Semi-supervised Graph Anomaly Detection
  45. ICLR 2026Towards Generalizable PDE Dynamics Forecasting via Physics-Guided Invariant Learning
  46. ICLR 2026Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interaction
  47. ICLR 2026Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness
  48. ICLR 2026Transformers Don’t Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and Implications for Mechanistic Interpretability
  49. ICLR 2026TreeGrad-Ranker: Feature Ranking via $O(L)$-Time Gradients for Decision Trees
  50. ICLR 2026TrimR: Verifier-based Training-Free Thinking Trimming for Efficient Test-Time Scaling

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