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 95 篇，第 1 / 2 页

1. ICLR 2024A Dynamical View of the Question of Why
2. ICLR 2024Active Test-Time Adaptation: Theoretical Analyses and An Algorithm
3. ICLR 2024Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
4. ICLR 2024Amortized Network Intervention to Steer the Excitatory Point Processes
5. ICLR 2024AmortizedPeriod: Attention-based Amortized Inference for Periodicity Identification
6. ICLR 2024ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning
7. ICLR 2024Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values
8. ICLR 2024Boosting Graph Anomaly Detection with Adaptive Message Passing
9. ICLR 2024C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
10. ICLR 2024CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting
11. ICLR 2024CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery
12. ICLR 2024ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs
13. ICLR 2024CNN Kernels Can Be the Best Shapelets
14. ICLR 2024Conditional Information Bottleneck Approach for Time Series Imputation
15. ICLR 2024Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited Supervision
16. ICLR 2024Contrastive Difference Predictive Coding
17. ICLR 2024Copula Conformal prediction for multi-step time series prediction
18. ICLR 2024DAM: Towards a Foundation Model for Forecasting
19. ICLR 2024Deep Orthogonal Hypersphere Compression for Anomaly Detection
20. ICLR 2024Diffusion-TS: Interpretable Diffusion for General Time Series Generation
21. ICLR 2024Disentangling Time Series Representations via Contrastive Independence-of-Support on l-Variational Inference
22. ICLR 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
23. ICLR 2024Explaining Time Series via Contrastive and Locally Sparse Perturbations
24. ICLR 2024Exploring Diffusion Time-steps for Unsupervised Representation Learning
25. ICLR 2024Feature-aligned N-BEATS with Sinkhorn divergence
26. ICLR 2024Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
27. ICLR 2024FITS: Modeling Time Series with $10k$ Parameters
28. ICLR 2024FreeDyG: Frequency Enhanced Continuous-Time Dynamic Graph Model for Link Prediction
29. ICLR 2024GAFormer: Enhancing Timeseries Transformers Through Group-Aware Embeddings
30. ICLR 2024Generative Learning for Financial Time Series with Irregular and Scale-Invariant Patterns
31. ICLR 2024Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs
32. ICLR 2024Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations
33. ICLR 2024HyperAttention: Long-context Attention in Near-Linear Time
34. ICLR 2024IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
35. ICLR 2024Incentive-Aware Federated Learning with Training-Time Model Rewards
36. ICLR 2024Inherently Interpretable Time Series Classification via Multiple Instance Learning
37. ICLR 2024Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series Prediction
38. ICLR 2024iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
39. ICLR 2024Language Models Represent Space and Time
40. ICLR 2024Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time
41. ICLR 2024Learning invariant representations of time-homogeneous stochastic dynamical systems
42. ICLR 2024Learning to Embed Time Series Patches Independently
43. ICLR 2024Let's do the time-warp-attend: Learning topological invariants of dynamical systems
44. ICLR 2024Leveraging Generative Models for Unsupervised Alignment of Neural Time Series Data
45. ICLR 2024Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time
46. ICLR 2024LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition
47. ICLR 2024MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods
48. ICLR 2024MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process
49. ICLR 2024ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis
50. ICLR 2024MOTOR: A Time-to-Event Foundation Model For Structured Medical Records

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。