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 585 篇，第 2 / 12 页

51. CVPR 2025Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures
52. CVPR 2025Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPs
53. CVPR 2025SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens
54. CVPR 2025ScaleLSD: Scalable Deep Line Segment Detection Streamlined
55. CVPR 2025Scaling Inference Time Compute for Diffusion Models
56. CVPR 2025SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding
57. CVPR 2025SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos
58. CVPR 2025Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering
59. CVPR 2025SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes
60. CVPR 2025SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity
61. CVPR 2025SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
62. CVPR 2025TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting
63. CVPR 2025Test-time Augmentation Improves Efficiency in Conformal Prediction
64. CVPR 2025Test-Time Backdoor Detection for Object Detection Models
65. CVPR 2025Test-Time Visual In-Context Tuning
66. CVPR 2025TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction
67. CVPR 2025Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields
68. CVPR 2025Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
69. CVPR 2025Towards Practical Real-Time Neural Video Compression
70. CVPR 2025Towards RAW Object Detection in Diverse Conditions
71. CVPR 2025Track Any Anomalous Object:A Granular Video Anomaly Detection Pipeline
72. CVPR 2025UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection
73. CVPR 2025Unraveling Normal Anatomy via Fluid-Driven Anomaly Randomization
74. CVPR 2025Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes
75. ICLR 2025A deep inverse-mapping model for a flapping robotic wing
76. ICLR 2025A Riemannian Framework for Learning Reduced-order Lagrangian Dynamics
77. ICLR 2025Adaptive Retention & Correction: Test-Time Training for Continual Learning
78. ICLR 2025Adversarially Robust Anomaly Detection through Spurious Negative Pair Mitigation
79. ICLR 2025Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems
80. ICLR 2025Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series
81. ICLR 2025AnoLLM: Large Language Models for Tabular Anomaly Detection
82. ICLR 2025AutoUAD: Hyper-parameter Optimization for Unsupervised Anomaly Detection
83. ICLR 2025Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations
84. ICLR 2025Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
85. ICLR 2025Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling
86. ICLR 2025Can LLMs Understand Time Series Anomalies?
87. ICLR 2025CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching
88. ICLR 2025CausalRivers - Scaling up benchmarking of causal discovery for real-world time-series
89. ICLR 2025Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player Games
90. ICLR 2025COME: Test-time Adaption by Conservatively Minimizing Entropy
91. ICLR 2025Compositional simulation-based inference for time series
92. ICLR 2025Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models
93. ICLR 2025CoMRes: Semi-Supervised Time Series Forecasting Utilizing Consensus Promotion of Multi-Resolution
94. ICLR 2025Context Steering: Controllable Personalization at Inference Time
95. ICLR 2025Context-Alignment: Activating and Enhancing LLMs Capabilities in Time Series
96. ICLR 2025Continual Slow-and-Fast Adaptation of Latent Neural Dynamics (CoSFan): Meta-Learning What-How & When to Adapt
97. ICLR 2025Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
98. ICLR 2025Controlling Space and Time with Diffusion Models
99. ICLR 2025Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis
100. ICLR 2025Differentially Private Federated Learning with Time-Adaptive Privacy Spending

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。