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 11 / 44 页

  1. ICML 2026Ranking Time Series using a Time Warping Ideal Point Model
  2. ICML 2026Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning
  3. ICML 2026RealtimeTool: Parallel Decoding for Real-Time LLM Function Calling
  4. ICML 2026ReAugment: Targeted Few-Shot Time Series Augmentation via Model Zoo-Guided Reinforcement Learning
  5. ICML 2026ReNF: Rethinking the Design of Neural Long-Term Time Series Forecasters
  6. ICML 2026Residual-Guided Multi-Resolution Refinement of Foundation Models: A Case Study in Drought Forecasting
  7. ICML 2026Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle
  8. ICML 2026Rethinking Multimodal Time-Series Forecasting Evaluation
  9. ICML 2026Rethinking Time-Series Imputation as Conditional Inference along Temporal Evolution
  10. ICML 2026Revealing Scaling Paradox in Large-scale Time Series Models: Implications for More Efficient and Accurate Forecasting
  11. ICML 2026Revisiting Neural Processes via Fourier Transform and Volterra Series
  12. ICML 2026Reviving Error Correction in Modern Deep Time-Series Forecasting
  13. ICML 2026Robust Causal Discovery in Real-World Time Series with Power-Laws
  14. ICML 2026Robust Inter-Series Dependency Modeling for Time Series Forecasting via Information-Theoretic Alignment
  15. ICML 2026Robustifying Vision-Language Models via Test-Time Prompt Adaptation
  16. ICML 2026RTInfer: Real-Time Inference of Multiple DNNs on Edge GPUs
  17. ICML 2026SafeCompass: Dynamic Chain-of-Thought Steering via Inference-Time Safety Signals
  18. ICML 2026Sampling from Your Language Model One Byte at a Time
  19. ICML 2026See More, Forecast Better and Faster: Enhancing Time Series Foundation Models via Inference-Time Plug-and-Play Downsampling
  20. ICML 2026Seeking Commonality, Preserving Specificity: A Spectral-Aware Hierarchical Framework for Cross-City Road Representation Learning
  21. ICML 2026SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement
  22. ICML 2026Self-Supervised Dynamical System Representations for Physiological Time-Series
  23. ICML 2026Shapley Regularized Neural Granger Causality
  24. ICML 2026Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
  25. ICML 2026Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases
  26. ICML 2026Sparse Regression with $\ell_0$ Constraints for $\alpha$-Mixing Time Series: Algorithms and Guarantees
  27. ICML 2026SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training
  28. ICML 2026StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
  29. ICML 2026StretchTime: Adaptive Time Series Forecasting via Symplectic Attention
  30. ICML 2026SubspacePath Pruner: Inference-time Pruning via Probe-based Representation–Parameter Coupling
  31. ICML 2026SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate
  32. ICML 2026Taming the Recent-Data Bias: Towards Robust Time Series Forecasting with Global Context
  33. ICML 2026TeamWork: Multivariate Time Series Anomaly Detection via Asymmetric Role-aware Channel Modeling
  34. ICML 2026TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis
  35. ICML 2026Terminal Dimension Reduction for Time Series with Applications
  36. ICML 2026Test-Time Graph Search for Goal-Conditioned Reinforcement Learning
  37. ICML 2026Test-Time Guidance for Flow-Based Generative Models via Parallel Tempering on Source Distributions
  38. ICML 2026Test-Time Learning of Causal Structure from Interventional Data
  39. ICML 2026Test-time Offline Reinforcement Learning on Goal-related Experience
  40. ICML 2026Test-Time Training with KV Binding Is Secretly Linear Attention
  41. ICML 2026TF-FACE: Time-Frequency Fusion Learning via Frequency-Domain Adaptive and Controllable Enhancement for Trajectory Prediction
  42. ICML 2026TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems
  43. ICML 2026Theoretical Investigation on Inductive Bias of Isolation Forest
  44. ICML 2026ThetaEvolve: Test-time Learning on Open Problems
  45. ICML 2026Time Series Forecasting Through the Lens of Dynamics
  46. ICML 2026Time series saliency maps: Explaining models across multiple domains
  47. ICML 2026Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces
  48. ICML 2026Time-Consistent Robust Multi-Objective Reinforcement Learning via a Bellman–Isaacs Weight-Adversary Recursion
  49. ICML 2026Time-PEFT: Temporal and Multichannel Complexity-Based Fine-Tuning for Time-Series Foundation Models
  50. ICML 2026Time-Series Decomposition as a Standalone Task: A Mechanism-Driven Diagnostic Benchmark

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