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 599 篇，第 9 / 12 页

401. ICML 2025TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting
402. ICML 2025TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting
403. ICML 2025TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation
404. ICML 2025TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting
405. ICML 2025TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning
406. ICML 2025TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state
407. ICML 2025TimeStacker: A Novel Framework with Multilevel Observation for Capturing Nonstationary Patterns in Time Series Forecasting
408. ICML 2025TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation
409. ICML 2025Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer
410. ICML 2025Towards a Unified Framework of Clustering-based Anomaly Detection
411. ICML 2025Towards Memorization Estimation: Fast, Formal and Free
412. ICML 2025Training High Performance Spiking Neural Network by Temporal Model Calibration
413. ICML 2025TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation
414. ICML 2025TTFSFormer: A TTFS-based Lossless Conversion of Spiking Transformer
415. ICML 2025Understanding and Improving Length Generalization in Recurrent Models
416. ICML 2025UnHiPPO: Uncertainty-aware Initialization for State Space Models
417. ICML 2025UniSim: A Unified Simulator for Time-Coarsened Dynamics of Biomolecules
418. ICML 2025VerbalTS: Generating Time Series from Texts
419. ICML 2025VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
420. ICML 2025WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting
421. ICML 2025When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network
422. ICML 2025When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series
423. ICML 2025Winner-takes-all for Multivariate Probabilistic Time Series Forecasting
424. ICML 2024$S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting
425. ICML 2024A decoder-only foundation model for time-series forecasting
426. ICML 2024A Dual-module Framework for Counterfactual Estimation over Time
427. ICML 2024A Language Model’s Guide Through Latent Space
428. ICML 2024A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)
429. ICML 2024A Near-Linear Time Approximation Algorithm for Beyond-Worst-Case Graph Clustering
430. ICML 2024A Subquadratic Time Algorithm for Robust Sparse Mean Estimation
431. ICML 2024ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data
432. ICML 2024An Analysis of Linear Time Series Forecasting Models
433. ICML 2024An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series
434. ICML 2024An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks
435. ICML 2024An Unsupervised Approach for Periodic Source Detection in Time Series
436. ICML 2024Arrows of Time for Large Language Models
437. ICML 2024BayOTIDE: Bayesian Online Multivariate Time Series Imputation with Functional Decomposition
438. ICML 2024Benign Overfitting in Adversarial Training of Neural Networks
439. ICML 2024Beyond Individual Input for Deep Anomaly Detection on Tabular Data
440. ICML 2024Bridging discrete and continuous state spaces: Exploring the Ehrenfest process in time-continuous diffusion models
441. ICML 2024CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables
442. ICML 2024CauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series
443. ICML 2024CLIPZyme: Reaction-Conditioned Virtual Screening of Enzymes
444. ICML 2024Conformal prediction for multi-dimensional time series by ellipsoidal sets
445. ICML 2024Conformalized Adaptive Forecasting of Heterogeneous Trajectories
446. ICML 2024Consistent Adversarially Robust Linear Classification: Non-Parametric Setting
447. ICML 2024Contamination-Resilient Anomaly Detection via Adversarial Learning on Partially-Observed Normal and Anomalous Data
448. ICML 2024Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time
449. ICML 2024Decoding-time Realignment of Language Models
450. ICML 2024Deep Functional Factor Models: Forecasting High-Dimensional Functional Time Series via Bayesian Nonparametric Factorization

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。