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 2,156 篇，第 12 / 44 页

551. ICML 2026TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
552. ICML 2026TimeLAVA: Learning-Agnostic Valuation for Time Series Data
553. ICML 2026TimeMRA: LLM-Empowered Time Series Forecasting via Multi-Scale Retrieval-Augmented Representations
554. ICML 2026TimeOmni-VL: Unified Models for Time Series Understanding and Generation
555. ICML 2026TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models
556. ICML 2026TimeSeed: Effective Time Series Forecasting with Sparse Endogenous Variables
557. ICML 2026TiMi: Empower Time Series Transformers with Multimodal Mixture of Experts
558. ICML 2026TopoDistill: Distilling Global System Topology for Causal Discovery in Multivariate Time Series
559. ICML 2026Towards a Unified Generative Model for Scarce Time Series with Domain Experts
560. ICML 2026Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy
561. ICML 2026Towards One-for-All Anomaly Detection for Tabular Data
562. ICML 2026Tri-Scale Neural ODEs for Continuous Multi-Omics Disease Modeling
563. ICML 2026TSFAdv: Frequency-Guided Black-Box Adversarial Attacks on Time Series Forecasting
564. ICML 2026TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction
565. ICML 2026TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models
566. ICML 2026Unfolded Laplacian Spectral Embedding: A Theoretically Grounded Approach to Dynamic Network Representation
567. ICML 2026Unified Time Series Explanations via Amortized Optimization and Instance-level Multi-Expert Knowledge Distillation
568. ICML 2026Universal Redundancies in Time Series Foundation Models
569. ICML 2026WaveSSM: Multiscale State-Space Models for Non-stationary Signal Attention
570. ICML 2026What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions
571. ICML 2026What If We Allocate Test-Time Compute Adaptively?
572. ICML 2026What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies
573. ICML 2026WildCat: Near-Linear Attention in Theory and Practice
574. ICML 2026Winformer: Transcending Pairwise Similarity for Time-series Generation
575. ICML 2026Words Towards Explainability: Caption Label-Free Learning via Dual Loop Agentic Time Series Captioning
576. ICML 2026ZeroDiff: Zero-Shot Time Series Reconstruction via Informed-Prior Diffusion
577. ICML 2026Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis
578. NeurIPS 2026A Batched Hartigan's $k$-Means Clustering
579. NeurIPS 2026A Locally Tokenized Generative Model for Robust Time-Series Watermarking
580. NeurIPS 2026A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
581. NeurIPS 2026A Scalable Multi-Task Model for Virtual Sensors
582. NeurIPS 2026A Scalable Nonparametric Continuous-Time Survival Model through Numerical Quadrature
583. NeurIPS 2026ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space
584. NeurIPS 2026Accelerating Safe Reinforcement Learning with Massive Parallelism
585. NeurIPS 2026ADA: Resolving Attribution Ambiguity in End-to-End Power System Dispatch via Two-Time-Scale Stochastic Approximation
586. NeurIPS 2026Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification
587. NeurIPS 2026AET-Bench: Pixel-Accurate Atomic Tomography Is Not Atom-Accurate
588. NeurIPS 2026AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting
589. NeurIPS 2026Amortized Linear-time Exact Shapley Value for Product-Kernel Methods
590. NeurIPS 2026Anytime-Valid PAC-Bayes Certificates for Adaptive Test-Time Scaling
591. NeurIPS 2026Archimedean Copula Inference via Taylor-Mode AD
592. NeurIPS 2026At FullTilt: Real-Time Open-Set 3D Macromolecule Detection Directly from Tilted 2D Projections
593. NeurIPS 2026AtmoZero: Self-Play Post-Training for Caption-Free Weather Time-Series Captioning
594. NeurIPS 2026Auditing Conformal Prediction for Language Models Under Inference-Time Model Shift
595. NeurIPS 2026Bayesian Preference Learning for Test-Time Steerable Reward Models
596. NeurIPS 2026Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback
597. NeurIPS 2026Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
598. NeurIPS 2026Benchmarking Sensor-Fault Robustness in Forecasting
599. NeurIPS 2026Best-of-$N$ Guidance for Test-time Diffusion Alignment
600. NeurIPS 2026Beyond Linear Decoders: Dynamic Expert-Coupled Optimal Decoding for Time Series Forecasting

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。