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 424 篇，第 2 / 9 页

51. CVPR 2024Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement
52. CVPR 2024Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis
53. CVPR 2024SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting
54. CVPR 2024Supervised Anomaly Detection for Complex Industrial Images
55. CVPR 2024T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory
56. CVPR 2024Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models
57. CVPR 2024TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression
58. CVPR 2024TEA: Test-time Energy Adaptation
59. CVPR 2024Test-Time Adaptation for Depth Completion
60. CVPR 2024Test-Time Domain Generalization for Face Anti-Spoofing
61. CVPR 2024Test-Time Linear Out-of-Distribution Detection
62. CVPR 2024The STVchrono Dataset: Towards Continuous Change Recognition in Time
63. CVPR 2024Time-Efficient Light-Field Acquisition Using Coded Aperture and Events
64. CVPR 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts
65. CVPR 2024UniMODE: Unified Monocular 3D Object Detection
66. CVPR 2024UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio Video Point Cloud Time-Series and Image Recognition
67. CVPR 2024Video-Based Human Pose Regression via Decoupled Space-Time Aggregation
68. CVPR 2024WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects Under Occlusion
69. ICLR 2024A Dynamical View of the Question of Why
70. ICLR 2024Active Test-Time Adaptation: Theoretical Analyses and An Algorithm
71. ICLR 2024Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
72. ICLR 2024Amortized Network Intervention to Steer the Excitatory Point Processes
73. ICLR 2024AmortizedPeriod: Attention-based Amortized Inference for Periodicity Identification
74. ICLR 2024ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning
75. ICLR 2024Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values
76. ICLR 2024Boosting Graph Anomaly Detection with Adaptive Message Passing
77. ICLR 2024C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
78. ICLR 2024CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting
79. ICLR 2024CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery
80. ICLR 2024ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs
81. ICLR 2024CNN Kernels Can Be the Best Shapelets
82. ICLR 2024Conditional Information Bottleneck Approach for Time Series Imputation
83. ICLR 2024Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited Supervision
84. ICLR 2024Contrastive Difference Predictive Coding
85. ICLR 2024Copula Conformal prediction for multi-step time series prediction
86. ICLR 2024DAM: Towards a Foundation Model for Forecasting
87. ICLR 2024Deep Orthogonal Hypersphere Compression for Anomaly Detection
88. ICLR 2024Diffusion-TS: Interpretable Diffusion for General Time Series Generation
89. ICLR 2024Disentangling Time Series Representations via Contrastive Independence-of-Support on l-Variational Inference
90. ICLR 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
91. ICLR 2024Explaining Time Series via Contrastive and Locally Sparse Perturbations
92. ICLR 2024Exploring Diffusion Time-steps for Unsupervised Representation Learning
93. ICLR 2024Feature-aligned N-BEATS with Sinkhorn divergence
94. ICLR 2024Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
95. ICLR 2024FITS: Modeling Time Series with $10k$ Parameters
96. ICLR 2024FreeDyG: Frequency Enhanced Continuous-Time Dynamic Graph Model for Link Prediction
97. ICLR 2024GAFormer: Enhancing Timeseries Transformers Through Group-Aware Embeddings
98. ICLR 2024Generative Learning for Financial Time Series with Irregular and Scale-Invariant Patterns
99. ICLR 2024Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs
100. ICLR 2024Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations

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。