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 272 篇，第 2 / 6 页

51. CVPR 2023TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation
52. CVPR 2023Test Time Adaptation With Regularized Loss for Weakly Supervised Salient Object Detection
53. CVPR 2023TIPI: Test Time Adaptation With Transformation Invariance
54. CVPR 2023Unsupervised Space-Time Network for Temporally-Consistent Segmentation of Multiple Motions
55. CVPR 2023UV Volumes for Real-Time Rendering of Editable Free-View Human Performance
56. CVPR 2023ViTs for SITS: Vision Transformers for Satellite Image Time Series
57. CVPR 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking
58. CVPR 2023YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors
59. CVPR 2023You Only Segment Once: Towards Real-Time Panoptic Segmentation
60. ICLR 2023A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
61. ICLR 2023Accelerating Hamiltonian Monte Carlo via Chebyshev Integration Time
62. ICLR 2023An Exact Poly-Time Membership-Queries Algorithm for Extracting a Three-Layer ReLU Network
63. ICLR 2023Anamnesic Neural Differential Equations with Orthogonal Polynomial Projections
64. ICLR 2023Autoregressive Conditional Neural Processes
65. ICLR 2023Can discrete information extraction prompts generalize across language models?
66. ICLR 2023Characteristic Neural Ordinary Differential Equation
67. ICLR 2023Characterizing the spectrum of the NTK via a power series expansion
68. ICLR 2023ChiroDiff: Modelling chirographic data with Diffusion Models
69. ICLR 2023Compositionality with Variation Reliably Emerges in Neural Networks
70. ICLR 2023Continuous-time identification of dynamic state-space models by deep subspace encoding
71. ICLR 2023Contrastive Learning for Unsupervised Domain Adaptation of Time Series
72. ICLR 2023CoRTX: Contrastive Framework for Real-time Explanation
73. ICLR 2023Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting
74. ICLR 2023CUTS: Neural Causal Discovery from Irregular Time-Series Data
75. ICLR 2023Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths
76. ICLR 2023DELTA: DEGRADATION-FREE FULLY TEST-TIME ADAPTATION
77. ICLR 2023Denoising Diffusion Error Correction Codes
78. ICLR 2023Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs
79. ICLR 2023Effectively Modeling Time Series with Simple Discrete State Spaces
80. ICLR 2023Efficient recurrent architectures through activity sparsity and sparse back-propagation through time
81. ICLR 2023Generalize Learned Heuristics to Solve Large-scale Vehicle Routing Problems in Real-time
82. ICLR 2023Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
83. ICLR 2023Koopman Neural Operator Forecaster for Time-series with Temporal Distributional Shifts
84. ICLR 2023Learning Fast and Slow for Online Time Series Forecasting
85. ICLR 2023Liquid Structural State-Space Models
86. ICLR 2023M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation
87. ICLR 2023MECTA: Memory-Economic Continual Test-Time Model Adaptation
88. ICLR 2023Memorization Capacity of Neural Networks with Conditional Computation
89. ICLR 2023Meta Temporal Point Processes
90. ICLR 2023MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting
91. ICLR 2023Multivariate Time-series Imputation with Disentangled Temporal Representations
92. ICLR 2023Out-of-distribution Detection with Implicit Outlier Transformation
93. ICLR 2023Out-of-distribution Representation Learning for Time Series Classification
94. ICLR 2023Phase transition for detecting a small community in a large network
95. ICLR 2023Real-Time Image Demoir$\acute{e}$ing on Mobile Devices
96. ICLR 2023Recursive Time Series Data Augmentation
97. ICLR 2023Red PANDA: Disambiguating Image Anomaly Detection by Removing Nuisance Factors
98. ICLR 2023Replicable Bandits
99. ICLR 2023Rhino: Deep Causal Temporal Relationship Learning with History-dependent Noise
100. ICLR 2023Riemannian Metric Learning via Optimal Transport

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。