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 23 / 44 页

  1. ICML 2025Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection
  2. ICML 2025CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling
  3. ICML 2025Channel Normalization for Time Series Channel Identification
  4. ICML 2025CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations
  5. ICML 2025Conditional Diffusion Model with Nonlinear Data Transformation for Time Series Forecasting
  6. ICML 2025Conformal Anomaly Detection in Event Sequences
  7. ICML 2025Context is Key: A Benchmark for Forecasting with Essential Textual Information
  8. ICML 2025Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games
  9. ICML 2025Continuously Updating Digital Twins using Large Language Models
  10. ICML 2025Demeaned Sparse: Efficient Anomaly Detection by Residual Estimate
  11. ICML 2025Deterministic Sparse Fourier Transform for Continuous Signals with Frequency Gap
  12. ICML 2025Discovering Latent Causal Graphs from Spatiotemporal Data
  13. ICML 2025Discovering Physics Laws of Dynamical Systems via Invariant Function Learning
  14. ICML 2025Discrepancy Minimization in Input-Sparsity Time
  15. ICML 2025Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity
  16. ICML 2025Efficient Personalized Adaptation for Physiological Signal Foundation Model
  17. ICML 2025Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
  18. ICML 2025Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization
  19. ICML 2025Exploring Representations and Interventions in Time Series Foundation Models
  20. ICML 2025Fast Min-$\epsilon$ Segmented Regression using Constant-Time Segment Merging
  21. ICML 2025FIC-TSC: Learning Time Series Classification with Fisher Information Constraint
  22. ICML 2025Finite-Time Analysis of Discrete-Time Stochastic Interpolants
  23. ICML 2025Finite-Time Convergence Rates in Stochastic Stackelberg Games with Smooth Algorithmic Agents
  24. ICML 2025Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification
  25. ICML 2025FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting
  26. ICML 2025Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update Time
  27. ICML 2025Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time Series
  28. ICML 2025Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit Problems
  29. ICML 2025GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers
  30. ICML 2025Heterogeneous Treatment Effect in Time-to-Event Outcomes: Harnessing Censored Data with Recursively Imputed Trees
  31. ICML 2025Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series
  32. ICML 2025HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting
  33. ICML 2025HyperIV: Real-time Implied Volatility Smoothing
  34. ICML 2025Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves
  35. ICML 2025IMTS is Worth Time $\times$ Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction
  36. ICML 2025In-Context Fine-Tuning for Time-Series Foundation Models
  37. ICML 2025Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models
  38. ICML 2025Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
  39. ICML 2025IT$^3$: Idempotent Test-Time Training
  40. ICML 2025ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset
  41. ICML 2025KAN-AD: Time Series Anomaly Detection with Kolmogorov–Arnold Networks
  42. ICML 2025KoNODE: Koopman-Driven Neural Ordinary Differential Equations with Evolving Parameters for Time Series Analysis
  43. ICML 2025LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization
  44. ICML 2025LAST SToP for Modeling Asynchronous Time Series
  45. ICML 2025Latent Variable Estimation in Bayesian Black-Litterman Models
  46. ICML 2025Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning
  47. ICML 2025Learning Changes in Graphon Attachment Network Models
  48. ICML 2025Learning Soft Sparse Shapes for Efficient Time-Series Classification
  49. ICML 2025Learning Survival Distributions with the Asymmetric Laplace Distribution
  50. ICML 2025Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains

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