时间序列论文趋势 2023–2026

主要结论

• 时间序列论文从 2023 年的 272 篇增长到 2026 年的 876 篇，三年间扩大到约 3.2 倍。
• NeurIPS 是发时间序列论文最多的会议，2023–2026 年共 757 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 6 篇增至 2026 年的 85 篇。
• 在「图与结构化数据」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的分子建模是 2.7 倍，时间序列是 3.2 倍。

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

• NeurIPS 2026A Batched Hartigan's $k$-Means Clustering
• ICML 2026A Control-Theoretic View of Mamba on Stability and Robustness
• ICLR 2026A Single Architecture for Representing Invariance Under Any Space Group
• CVPR 2026Activation Matters Test-time Activated Negative Labels for OOD Detection with
• NeurIPS 2025Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency
• ICML 2025$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
• ICLR 2025A deep inverse-mapping model for a flapping robotic wing
• CVPR 2025Beyond Single-Modal Boundary: Cross-Modal Anomaly Detection through Visual Prototype and Harmonization
• NeurIPS 2024A Continuous-time Stochastic Gradient Descent Method for Continuous Data
• ICML 2024$S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting
• ICLR 2024ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning
• CVPR 2024Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation
• NeurIPS 2023A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time
• ICML 2023Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time
• ICLR 2023A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• CVPR 2023ActMAD: Activation Matching To Align Distributions for Test-Time-Training
• NeurIPS 2026A Locally Tokenized Generative Model for Robust Time-Series Watermarking
• ICML 2026ADHD Disease Detection Based on Short- and Long-Term Brain Function Encoding and Memory Graph Network
• ICLR 2026A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems
• CVPR 2026Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis

全部时间序列论文

共 599 篇，第 1 / 12 页

1. ICML 2026(1D) Ordered Tokens Enable Efficient Test-Time Search
2. ICML 2026A Control-Theoretic View of Mamba on Stability and Robustness
3. ICML 2026A Decision-Theoretic View of Test-Time Training: When, How Far, and Which Directions to Adapt
4. ICML 2026A robust PPG foundation model using multimodal physiological supervision
5. ICML 2026A Spiking Heterogeneous Harmonic Resonate-and-Fire State Space Model for Time Series
6. ICML 2026A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow Matching
7. ICML 2026Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis
8. ICML 2026AdaMEM: Test-Time Adaptive Memory for Language Agents
9. ICML 2026ADHD Disease Detection Based on Short- and Long-Term Brain Function Encoding and Memory Graph Network
10. ICML 2026Adversarially Robust Approximate Furthest Neighbor
11. ICML 2026Anti-Aliasing Matters: A Dynamic Network for Time Series Forecasting
12. ICML 2026AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding
13. ICML 2026ATLAS: Learning to Optimally Memorize the Context at Test Time
14. ICML 2026Automatic Unsupervised Ensemble Outlier Model Selection
15. ICML 2026Baguan-TS: dual in-context learning model for time series forecasting with covariates
16. ICML 2026BEDTime: A Unified Benchmark for Automatically Describing Time Series
17. ICML 2026Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting
18. ICML 2026Beyond Extrapolation: Knowledge Utilization Paradigm with Bidirectional Inspiration for Time Series Forecasting
19. ICML 2026Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting
20. ICML 2026Beyond Point Predictions: Manifold Expansion and Dual Alignment for Robust Time Series Distillation
21. ICML 2026Bio-Inspired Self-Supervised Learning for Wrist-worn Accelerometer Data
22. ICML 2026BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series
23. ICML 2026Bootstrapped Exploration with Causal Reasoning: A Training Paradigm for Adaptive Forecasting Agent
24. ICML 2026Branching Diffusion for Point Processes in Time and Space
25. ICML 2026Bregman meets Lévy: Stochastic Mirror Descent with Heavy-Tailed Noise in Continuous and Discrete Time
26. ICML 2026Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecasting
27. ICML 2026Byte Pair Encoding for Efficient Time Series Forecasting
28. ICML 2026Calibrated Test-Time Guidance for Bayesian Inference
29. ICML 2026Causal Discovery for Irregularly Time Series with Consistency Guarantees
30. ICML 2026Causal discovery for time series with endogenous context variables
31. ICML 2026Causal-aware Anomaly Detection for Tabular Data
32. ICML 2026CausalX: A Unified and Causally-Interpretable Plug-and-Play Model for Multi-modal Spatio-Temporal Forecasting
33. ICML 2026Channel Adapter for Time Series Foundation Models in Zero-Shot Multivariate Forecasting
34. ICML 2026CHESS: Chebyshev Spectral Synthesis for Trajectory Condensation
35. ICML 2026Cluster-Aware Causal Mixer for Online Anomaly Detection in Multivariate Time Series
36. ICML 2026CoGenCast: A Coupled Autoregressive–Flow Generative Framework for Time Series Forecasting
37. ICML 2026COGNOS: Universal Enhancement for Time Series Anomaly Detection via Constrained Gaussian-Noise Optimization and Smoothing
38. ICML 2026CombinationTS: A Modular Framework for Understanding Time-Series Forecasting Models
39. ICML 2026Component-Wise Composite Likelihood Distillation for Censored Time-to-Event Data
40. ICML 2026Conditional Quantile Adjusted Conformal Prediction for Time Series
41. ICML 2026ConFlux: Multivariate Time Series in Flux, One Unified Forecast in Confluence
42. ICML 2026Constrained Meta Reinforcement Learning with Provable Test-Time Safety
43. ICML 2026Continuous-Time Piecewise-Linear Recurrent Neural Networks
44. ICML 2026Controlled Dynamics Attractor Transformer
45. ICML 2026ConTSG-Bench: A Unified Benchmark for Conditional Time Series Generation
46. ICML 2026Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates
47. ICML 2026Credibility-Aware Weighting Federated Causal Discovery for Time Series
48. ICML 2026Crisp: A Spectral-Based Interaction Strategy for Multivariate Time Series Forecasting
49. ICML 2026CURE: Context-driven Diffusion with Progressive Expansion for Single Domain Generalization in Time Series Classification
50. ICML 2026D$^2$O: A Dual Debiasing Operator for Training-Free Test-Time Adaptation of Vision–Language Models

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。