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 60 篇，第 1 / 2 页

1. ICLR 2023A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
2. ICLR 2023Accelerating Hamiltonian Monte Carlo via Chebyshev Integration Time
3. ICLR 2023An Exact Poly-Time Membership-Queries Algorithm for Extracting a Three-Layer ReLU Network
4. ICLR 2023Anamnesic Neural Differential Equations with Orthogonal Polynomial Projections
5. ICLR 2023Autoregressive Conditional Neural Processes
6. ICLR 2023Can discrete information extraction prompts generalize across language models?
7. ICLR 2023Characteristic Neural Ordinary Differential Equation
8. ICLR 2023Characterizing the spectrum of the NTK via a power series expansion
9. ICLR 2023ChiroDiff: Modelling chirographic data with Diffusion Models
10. ICLR 2023Compositionality with Variation Reliably Emerges in Neural Networks
11. ICLR 2023Continuous-time identification of dynamic state-space models by deep subspace encoding
12. ICLR 2023Contrastive Learning for Unsupervised Domain Adaptation of Time Series
13. ICLR 2023CoRTX: Contrastive Framework for Real-time Explanation
14. ICLR 2023Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting
15. ICLR 2023CUTS: Neural Causal Discovery from Irregular Time-Series Data
16. ICLR 2023Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths
17. ICLR 2023DELTA: DEGRADATION-FREE FULLY TEST-TIME ADAPTATION
18. ICLR 2023Denoising Diffusion Error Correction Codes
19. ICLR 2023Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs
20. ICLR 2023Effectively Modeling Time Series with Simple Discrete State Spaces
21. ICLR 2023Efficient recurrent architectures through activity sparsity and sparse back-propagation through time
22. ICLR 2023Generalize Learned Heuristics to Solve Large-scale Vehicle Routing Problems in Real-time
23. ICLR 2023Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
24. ICLR 2023Koopman Neural Operator Forecaster for Time-series with Temporal Distributional Shifts
25. ICLR 2023Learning Fast and Slow for Online Time Series Forecasting
26. ICLR 2023Liquid Structural State-Space Models
27. ICLR 2023M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation
28. ICLR 2023MECTA: Memory-Economic Continual Test-Time Model Adaptation
29. ICLR 2023Memorization Capacity of Neural Networks with Conditional Computation
30. ICLR 2023Meta Temporal Point Processes
31. ICLR 2023MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting
32. ICLR 2023Multivariate Time-series Imputation with Disentangled Temporal Representations
33. ICLR 2023Out-of-distribution Detection with Implicit Outlier Transformation
34. ICLR 2023Out-of-distribution Representation Learning for Time Series Classification
35. ICLR 2023Phase transition for detecting a small community in a large network
36. ICLR 2023Real-Time Image Demoir$\acute{e}$ing on Mobile Devices
37. ICLR 2023Recursive Time Series Data Augmentation
38. ICLR 2023Red PANDA: Disambiguating Image Anomaly Detection by Removing Nuisance Factors
39. ICLR 2023Replicable Bandits
40. ICLR 2023Rhino: Deep Causal Temporal Relationship Learning with History-dependent Noise
41. ICLR 2023Riemannian Metric Learning via Optimal Transport
42. ICLR 2023Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms
43. ICLR 2023Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting
44. ICLR 2023Score-based Continuous-time Discrete Diffusion Models
45. ICLR 2023Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting
46. ICLR 2023Spatial Attention Kinetic Networks with E(n)-Equivariance
47. ICLR 2023SpeedyZero: Mastering Atari with Limited Data and Time
48. ICLR 2023Subquadratic Algorithms for Kernel Matrices via Kernel Density Estimation
49. ICLR 2023TEMPERA: Test-Time Prompt Editing via Reinforcement Learning
50. ICLR 2023Temporal Dependencies in Feature Importance for Time Series Prediction

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。