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 131 篇，第 1 / 3 页

1. ICLR 2025A deep inverse-mapping model for a flapping robotic wing
2. ICLR 2025A Riemannian Framework for Learning Reduced-order Lagrangian Dynamics
3. ICLR 2025Adaptive Retention & Correction: Test-Time Training for Continual Learning
4. ICLR 2025Adversarially Robust Anomaly Detection through Spurious Negative Pair Mitigation
5. ICLR 2025Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems
6. ICLR 2025Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series
7. ICLR 2025AnoLLM: Large Language Models for Tabular Anomaly Detection
8. ICLR 2025AutoUAD: Hyper-parameter Optimization for Unsupervised Anomaly Detection
9. ICLR 2025Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations
10. ICLR 2025Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
11. ICLR 2025Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling
12. ICLR 2025Can LLMs Understand Time Series Anomalies?
13. ICLR 2025CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching
14. ICLR 2025CausalRivers - Scaling up benchmarking of causal discovery for real-world time-series
15. ICLR 2025Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player Games
16. ICLR 2025COME: Test-time Adaption by Conservatively Minimizing Entropy
17. ICLR 2025Compositional simulation-based inference for time series
18. ICLR 2025Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models
19. ICLR 2025CoMRes: Semi-Supervised Time Series Forecasting Utilizing Consensus Promotion of Multi-Resolution
20. ICLR 2025Context Steering: Controllable Personalization at Inference Time
21. ICLR 2025Context-Alignment: Activating and Enhancing LLMs Capabilities in Time Series
22. ICLR 2025Continual Slow-and-Fast Adaptation of Latent Neural Dynamics (CoSFan): Meta-Learning What-How & When to Adapt
23. ICLR 2025Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
24. ICLR 2025Controlling Space and Time with Diffusion Models
25. ICLR 2025Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis
26. ICLR 2025Differentially Private Federated Learning with Time-Adaptive Privacy Spending
27. ICLR 2025DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector
28. ICLR 2025Diffusion Transformers for Tabular Data Time Series Generation
29. ICLR 2025Diffusion-based Decoupled Deterministic and Uncertain Framework for Probabilistic Multivariate Time Series Forecasting
30. ICLR 2025DRL: Decomposed Representation Learning for Tabular Anomaly Detection
31. ICLR 2025DyCAST: Learning Dynamic Causal Structure from Time Series
32. ICLR 2025Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models
33. ICLR 2025Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement
34. ICLR 2025Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions
35. ICLR 2025Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
36. ICLR 2025Efficiently Parameterized Neural Metriplectic Systems
37. ICLR 2025Error-quantified Conformal Inference for Time Series
38. ICLR 2025Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting
39. ICLR 2025FACTS: A Factored State-Space Framework for World Modelling
40. ICLR 2025Fast and Slow Streams for Online Time Series Forecasting Without Information Leakage
41. ICLR 2025Federated Granger Causality Learning For Interdependent Clients With State Space Representation
42. ICLR 2025Feedback Favors the Generalization of Neural ODEs
43. ICLR 2025Filtered not Mixed: Filtering-Based Online Gating for Mixture of Large Language Models
44. ICLR 2025Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond
45. ICLR 2025Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
46. ICLR 2025FreDF: Learning to Forecast in the Frequency Domain
47. ICLR 2025From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics
48. ICLR 2025Going Beyond Static: Understanding Shifts with Time-Series Attribution
49. ICLR 2025HR-Extreme: A High-Resolution Dataset for Extreme Weather Forecasting
50. ICLR 2025Identifying latent state transitions in non-linear dynamical systems

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。