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 220 篇，第 3 / 5 页

101. ICLR 2026Learning-Time Encoding Shapes Unlearning in LLMs
102. ICLR 2026Local Geometry Attention for Time Series Forecasting under Realistic Corruptions
103. ICLR 2026Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model?
104. ICLR 2026Low Rank Transformer for Multivariate Time Series Anomaly Detection and Localization
105. ICLR 2026MambaSL: Exploring Single-Layer Mamba for Time Series Classification
106. ICLR 2026MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
107. ICLR 2026Micro-Macro Coupled Koopman Modeling on Graph for Traffic Flow Prediction
108. ICLR 2026Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding Adjustment
109. ICLR 2026MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with $0.1K$ Parameters
110. ICLR 2026MMPD: Diverse Time Series Forecasting via Multi-Mode Patch Diffusion Loss
111. ICLR 2026Mode-conditioning unlocks superior test-time compute scaling
112. ICLR 2026Motion Prior Distillation in Time Reversal Sampling for Generative Inbetweening
113. ICLR 2026Multi-Scale Hypergraph Meets LLMs: Aligning Large Language Models for Time Series Analysis
114. ICLR 2026Noise Tolerance of Distributionally Robust Learning
115. ICLR 2026Numerion: A Multi-Hypercomplex Model for Time Series Forecasting
116. ICLR 2026ODEBrain: Continuous-Time EEG Graph for Modeling Dynamic Brain Networks
117. ICLR 2026On learning linear dynamical systems in context with attention layers
118. ICLR 2026Online Decision Making with Generative Action Sets
119. ICLR 2026Online time series prediction using feature adjustment
120. ICLR 2026Orbital Transformers for Predicting Wavefunctions in Time-Dependent Density Functional Theory
121. ICLR 2026Otters: An Energy-Efficient Spiking Transformer via Optical Time-to-First-Spike Encoding
122. ICLR 2026Overlap-weighted orthogonal meta-learner for treatment effect estimation over time
123. ICLR 2026PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection
124. ICLR 2026Panda: A pretrained forecast model for chaotic dynamics
125. ICLR 2026Parameterized Hardness of Zonotope Containment and Neural Network Verification
126. ICLR 2026PERSISTENCE SPHERES: BI-CONTINUOUS REPRESENTATIONS OF PERSISTENCE DIAGRAMS.
127. ICLR 2026Perturbed Dynamic Time Warping: A Probabilistic Framework and Generalized Variants
128. ICLR 2026PGRF-Net: A Prototype-Guided Relational Fusion Network for Diagnostic Multivariate Time-Series Anomaly Detection
129. ICLR 2026PhaseFormer: From Patches to Phases for Efficient and Effective Time Series Forecasting
130. ICLR 2026PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecasting
131. ICLR 2026PINFDiT: Energy-Based Physics-Informed Diffusion Transformers for General-purpose Time Series Tasks
132. ICLR 2026PIRN: Prototypical-based Intra-modal Reconstruction with Normality Communication for Multi-modal Anomaly Detection.
133. ICLR 2026Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models
134. ICLR 2026PMDformer: Patch-Mean Decoupling Transformer for Long-term Forecasting
135. ICLR 2026Prior-free Tabular Test-time Adaptation
136. ICLR 2026Priors in time: Missing inductive biases for language model interpretability
137. ICLR 2026ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting
138. ICLR 2026Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification
139. ICLR 2026PYRREGULAR: A Unified Framework for Irregular Time Series, with Classification Benchmarks
140. ICLR 2026Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models
141. ICLR 2026R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability
142. ICLR 2026RACE Attention: A Strictly Linear-Time Attention for Long-Sequence Training
143. ICLR 2026Random Controlled Differential Equations
144. ICLR 2026Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgment
145. ICLR 2026Reasoning on Time-Series for Financial Technical Analysis
146. ICLR 2026Reliable Probabilistic Forecasting of Irregular Time Series through Marginalization-Consistent Flows
147. ICLR 2026Representation-Based Exploration for Language Models: From Test-Time to Post-Training
148. ICLR 2026Repurposing Foundation Model for Generalizable Medical Time Series Classification
149. ICLR 2026ResCP: Reservoir Conformal Prediction for Time Series Forecasting
150. ICLR 2026ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection

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。