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 159 篇，第 1 / 4 页

1. ICML 2025$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
2. ICML 2025A Closer Look at Transformers for Time Series Forecasting: Understanding Why They Work and Where They Struggle
3. ICML 2025A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments
4. ICML 2025A Non-isotropic Time Series Diffusion Model with Moving Average Transitions
5. ICML 2025Active Learning with Selective Time-Step Acquisition for PDEs
6. ICML 2025AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting
7. ICML 2025AEQA-NAT : Adaptive End-to-end Quantization Alignment Training Framework for Non-autoregressive Machine Translation
8. ICML 2025An Architecture Search Framework for Inference-Time Techniques
9. ICML 2025An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions
10. ICML 2025Anytime-Constrained Equilibria in Polynomial Time
11. ICML 2025Arrow: Accelerator for Time Series Causal Discovery with Time Weaving
12. ICML 2025Automatic Differentiation of Optimization Algorithms with Time-Varying Updates
13. ICML 2025Bayesian Basis Function Approximation for Scalable Gaussian Process Priors in Deep Generative Models
14. ICML 2025BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
15. ICML 2025Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation
16. ICML 2025Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
17. ICML 2025BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling
18. ICML 2025Calibrating Video Watch-time Predictions with Credible Prototype Alignment
19. ICML 2025Categorical Schrödinger Bridge Matching
20. ICML 2025Causal Discovery from Conditionally Stationary Time Series
21. ICML 2025Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection
22. ICML 2025CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling
23. ICML 2025Channel Normalization for Time Series Channel Identification
24. ICML 2025CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations
25. ICML 2025Conditional Diffusion Model with Nonlinear Data Transformation for Time Series Forecasting
26. ICML 2025Conformal Anomaly Detection in Event Sequences
27. ICML 2025Context is Key: A Benchmark for Forecasting with Essential Textual Information
28. ICML 2025Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games
29. ICML 2025Continuously Updating Digital Twins using Large Language Models
30. ICML 2025Demeaned Sparse: Efficient Anomaly Detection by Residual Estimate
31. ICML 2025Deterministic Sparse Fourier Transform for Continuous Signals with Frequency Gap
32. ICML 2025Discovering Latent Causal Graphs from Spatiotemporal Data
33. ICML 2025Discovering Physics Laws of Dynamical Systems via Invariant Function Learning
34. ICML 2025Discrepancy Minimization in Input-Sparsity Time
35. ICML 2025Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity
36. ICML 2025Efficient Personalized Adaptation for Physiological Signal Foundation Model
37. ICML 2025Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
38. ICML 2025Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization
39. ICML 2025Exploring Representations and Interventions in Time Series Foundation Models
40. ICML 2025Fast Min-$\epsilon$ Segmented Regression using Constant-Time Segment Merging
41. ICML 2025FIC-TSC: Learning Time Series Classification with Fisher Information Constraint
42. ICML 2025Finite-Time Analysis of Discrete-Time Stochastic Interpolants
43. ICML 2025Finite-Time Convergence Rates in Stochastic Stackelberg Games with Smooth Algorithmic Agents
44. ICML 2025Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification
45. ICML 2025FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting
46. ICML 2025Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update Time
47. ICML 2025Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time Series
48. ICML 2025Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit Problems
49. ICML 2025GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers
50. ICML 2025Heterogeneous Treatment Effect in Time-to-Event Outcomes: Harnessing Censored Data with Recursively Imputed Trees

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。