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 2 / 4 页

51. ICML 2025Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series
52. ICML 2025HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting
53. ICML 2025HyperIV: Real-time Implied Volatility Smoothing
54. ICML 2025Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves
55. ICML 2025IMTS is Worth Time $\times$ Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction
56. ICML 2025In-Context Fine-Tuning for Time-Series Foundation Models
57. ICML 2025Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models
58. ICML 2025Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
59. ICML 2025IT$^3$: Idempotent Test-Time Training
60. ICML 2025ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset
61. ICML 2025KAN-AD: Time Series Anomaly Detection with Kolmogorov–Arnold Networks
62. ICML 2025KoNODE: Koopman-Driven Neural Ordinary Differential Equations with Evolving Parameters for Time Series Analysis
63. ICML 2025LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization
64. ICML 2025LAST SToP for Modeling Asynchronous Time Series
65. ICML 2025Latent Variable Estimation in Bayesian Black-Litterman Models
66. ICML 2025Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning
67. ICML 2025Learning Changes in Graphon Attachment Network Models
68. ICML 2025Learning Soft Sparse Shapes for Efficient Time-Series Classification
69. ICML 2025Learning Survival Distributions with the Asymmetric Laplace Distribution
70. ICML 2025Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains
71. ICML 2025Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes
72. ICML 2025Learning to (Learn at Test Time): RNNs with Expressive Hidden States
73. ICML 2025Learning with Exact Invariances in Polynomial Time
74. ICML 2025LETS Forecast: Learning Embedology for Time Series Forecasting
75. ICML 2025LightGTS: A Lightweight General Time Series Forecasting Model
76. ICML 2025Lightweight Online Adaption for Time Series Foundation Model Forecasts
77. ICML 2025Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting
78. ICML 2025LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data
79. ICML 2025LSCD: Lomb--Scargle Conditioned Diffusion for Time series Imputation
80. ICML 2025Masked Generative Nested Transformers with Decode Time Scaling
81. ICML 2025Measuring In-Context Computation Complexity via Hidden State Prediction
82. ICML 2025Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?
83. ICML 2025Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
84. ICML 2025MTSTRec: Multimodal Time-Aligned Shared Token Recommender
85. ICML 2025Non-stationary Diffusion For Probabilistic Time Series Forecasting
86. ICML 2025Nonlinear transformers can perform inference-time feature learning
87. ICML 2025Not All Tokens Matter All The Time: Dynamic Token Aggregation Towards Efficient Detection Transformers
88. ICML 2025OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial Distillation
89. ICML 2025Optimal Information Retention for Time-Series Explanations
90. ICML 2025Optimization Proxies using Limited Labeled Data and Training Time -- A Semi-Supervised Bayesian Neural Network Approach
91. ICML 2025Optimizing Language Models for Inference Time Objectives using Reinforcement Learning
92. ICML 2025Patch-wise Structural Loss for Time Series Forecasting
93. ICML 2025Polynomial Time Learning Augmented Algorithms for NP-hard Permutation Problems
94. ICML 2025Polynomial-Time Approximability of Constrained Reinforcement Learning
95. ICML 2025Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models
96. ICML 2025Position: It Is Time We Test Neural Computation In Vitro
97. ICML 2025Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting
98. ICML 2025ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation
99. ICML 2025Provable Length Generalization in Sequence Prediction via Spectral Filtering
100. ICML 2025PTTA: Purifying Malicious Samples for Test-Time Model Adaptation

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。