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 131 篇，第 2 / 3 页

51. ICLR 2025In-context Time Series Predictor
52. ICLR 2025InstaTrain: Adaptive Training via Ultra-Fast Natural Annealing within Dynamical Systems
53. ICLR 2025Intelligence at the Edge of Chaos
54. ICLR 2025Investigating Pattern Neurons in Urban Time Series Forecasting
55. ICLR 2025Kernel-based Optimally Weighted Conformal Time-Series Prediction
56. ICLR 2025KooNPro: A Variance-Aware Koopman Probabilistic Model Enhanced by Neural Process for Time Series Forecasting
57. ICLR 2025Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation Data
58. ICLR 2025Learn hybrid prototypes for multivariate time series anomaly detection
59. ICLR 2025Learning Chaos In A Linear Way
60. ICLR 2025Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data
61. ICLR 2025Learning Successor Features with Distributed Hebbian Temporal Memory
62. ICLR 2025Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio Test
63. ICLR 2025Learning under Temporal Label Noise
64. ICLR 2025Learning vector fields of differential equations on manifolds with geometrically constrained operator-valued kernels
65. ICLR 2025LevAttention: Time, Space and Streaming Efficient Algorithm for Heavy Attentions
66. ICLR 2025Locally Connected Echo State Networks for Time Series Forecasting
67. ICLR 2025Long-Context Linear System Identification
68. ICLR 2025Long-time asymptotics of noisy SVGD outside the population limit
69. ICLR 2025MamKO: Mamba-based Koopman operator for modeling and predictive control
70. ICLR 2025Mask in the Mirror: Implicit Sparsification
71. ICLR 2025Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling
72. ICLR 2025Model-agnostic meta-learners for estimating heterogeneous treatment effects over time
73. ICLR 2025Modeling Complex System Dynamics with Flow Matching Across Time and Conditions
74. ICLR 2025MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection
75. ICLR 2025MuHBoost: Multi-Label Boosting For Practical Longitudinal Human Behavior Modeling
76. ICLR 2025Multi-Label Test-Time Adaptation with Bound Entropy Minimization
77. ICLR 2025Multi-Resolution Decomposable Diffusion Model for Non-Stationary Time Series Anomaly Detection
78. ICLR 2025Neural Context Flows for Meta-Learning of Dynamical Systems
79. ICLR 2025Neural Functions for Learning Periodic Signal
80. ICLR 2025Node-Time Conditional Prompt Learning in Dynamic Graphs
81. ICLR 2025Noisy Test-Time Adaptation in Vision-Language Models
82. ICLR 2025Nonlinear Sequence Embedding by Monotone Variational Inequality
83. ICLR 2025On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning
84. ICLR 2025On the Adversarial Vulnerability of Label-Free Test-Time Adaptation
85. ICLR 2025Optimal Transport for Time Series Imputation
86. ICLR 2025Oscillatory State-Space Models
87. ICLR 2025PAD: Personalized Alignment of LLMs at Decoding-time
88. ICLR 2025PaPaGei: Open Foundation Models for Optical Physiological Signals
89. ICLR 2025Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time-Series Forecasting Based on Biological ODEs
90. ICLR 2025Poisson-Dirac Neural Networks for Modeling Coupled Dynamical Systems across Domains
91. ICLR 2025PPT: Patch Order Do Matters In Time Series Pretext Task
92. ICLR 2025RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data
93. ICLR 2025Robust System Identification: Finite-sample Guarantees and Connection to Regularization
94. ICLR 2025Root Cause Analysis of Anomalies in Multivariate Time Series through Granger Causal Discovery
95. ICLR 2025S4M: S4 for multivariate time series forecasting with Missing values
96. ICLR 2025Scalable Mechanistic Neural Networks
97. ICLR 2025Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning
98. ICLR 2025Selective Label Enhancement Learning for Test-Time Adaptation
99. ICLR 2025Self-supervised contrastive learning performs non-linear system identification
100. ICLR 2025Shedding Light on Time Series Classification using Interpretability Gated Networks

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。