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 220 篇，第 2 / 5 页

51. ICLR 2026Distribution-informed Online Conformal Prediction
52. ICLR 2026DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Series
53. ICLR 2026Dual Distillation for Few-Shot Anomaly Detection
54. ICLR 2026e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
55. ICLR 2026Edit-Based Flow Matching for Temporal Point Processes
56. ICLR 2026Eliciting Numerical Predictive Distributions of LLMs Without Auto-Regression
57. ICLR 2026End-to-End Probabilistic Framework for Learning with Hard Constraints
58. ICLR 2026Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval
59. ICLR 2026Enhancing Sparse Event Detection in Healthcare Time-Series via Adaptive Gate of Context–Detail Interaction
60. ICLR 2026EVEREST: A Transformer for Probabilistic Rare-Event Anomaly Detection with Evidential and Tail-Aware Uncertainty
61. ICLR 2026Exploring Real-Time Super-Resolution: Benchmarking and Fine-Tuning for Streaming Content
62. ICLR 2026Exposing Mixture and Annotating Confusion for Active Universal Test-Time Adaptation
63. ICLR 2026Extreme Weather Nowcasting via Local Precipitation Pattern Prediction
64. ICLR 2026FACT: Fine-grained Across-variable Convolution for Multivariate Time Series Forecasting
65. ICLR 2026FeDaL: Federated Dataset Learning for General Time Series Foundation Models
66. ICLR 2026Finite-Time Analysis of Actor-Critic Methods with Deep Neural Network Approximation
67. ICLR 2026Finite-Time Convergence Analysis of ODE-based Generative Models for Stochastic Interpolants
68. ICLR 2026Flow-based Conformal Prediction for Multi-dimensional Time Series
69. ICLR 2026Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning
70. ICLR 2026Free Point-wise Anomaly Detection via Fold-bifurcation
71. ICLR 2026From Curiosity to Caution: Mitigating Reward Hacking for Best-of-$N$ with Pessimism
72. ICLR 2026From Samples to Scenarios: A New Paradigm for Probabilistic Forecasting
73. ICLR 2026GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Care
74. ICLR 2026GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables
75. ICLR 2026Generative Diffusion Prior Distillation for Long-Context Knowledge Transfer
76. ICLR 2026GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series data
77. ICLR 2026GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
78. ICLR 2026Harnessing Temporal Databases for Systematic Evaluation of Factual Time-Sensitive Question-Answering in LLMs
79. ICLR 2026HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series
80. ICLR 2026HiVid: LLM-Guided Video Saliency For Content-Aware VOD And Live Streaming
81. ICLR 2026How to Lose Inherent Counterfactuality in Reinforcement Learning
82. ICLR 2026ICDiffAD: Implicit Conditioning Diffusion Model for Time Series Anomaly Detection
83. ICLR 2026Identifiability Challenges in Sparse Linear Ordinary Differential Equations
84. ICLR 2026IGC-Net for conditional average potential outcome estimation over time
85. ICLR 2026Implicit Models: Expressive Power Scales with Test-Time Compute
86. ICLR 2026In-Place Test-Time Training
87. ICLR 2026Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification
88. ICLR 2026Inference-Time Personalized Safety Control via Paired Difference-in-Means Intervention
89. ICLR 2026Inoculation Prompting: Eliciting traits from LLMs during training can reduce trait expression at test-time
90. ICLR 2026It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization
91. ICLR 2026Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative
92. ICLR 2026Latent-to-Data Cascaded Diffusion Models for Unconditional Time Series Generation
93. ICLR 2026Learning in Prophet Inequalities with Noisy Observations
94. ICLR 2026Learning Koopman Representations with Controllability Guarantees
95. ICLR 2026Learning linear state-space models with sparse system matrices
96. ICLR 2026Learning Mixtures of Linear Dynamical Systems (MoLDS) via Hybrid Tensor–EM Method
97. ICLR 2026Learning Recursive Multi-Scale Representations for Irregular Multivariate Time Series Forecasting
98. ICLR 2026Learning Shrinks the Hard Tail: Training‑Dependent Inference Scaling in a Solvable Linear Model
99. ICLR 2026Learning to Solve Orienteering Problem with Time Windows and Variable Profits
100. ICLR 2026Learning-Augmented Moment Estimation on Time-Decay 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。