时间序列论文趋势 2023–2026

预测与异常检测

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,157 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

时间序列论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202391606259272
20241479511468424
202522113115974585
202629822026494876

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

全部时间序列论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 2,156 篇，第 22 / 44 页

  1. ICLR 2025SigDiffusions: Score-Based Diffusion Models for Time Series via Log-Signature Embeddings
  2. ICLR 2025SimpleTM: A Simple Baseline for Multivariate Time Series Forecasting
  3. ICLR 2025Simplifying, Stabilizing and Scaling Continuous-time Consistency Models
  4. ICLR 2025Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent Learning
  5. ICLR 2025SMITE: Segment Me In TimE
  6. ICLR 2025Specialized Foundation Models Struggle to Beat Supervised Baselines
  7. ICLR 2025Stabilized Neural Prediction of Potential Outcomes in Continuous Time
  8. ICLR 2025Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models
  9. ICLR 2025Synthesizing Realistic fMRI: A Physiological Dynamics-Driven Hierarchical Diffusion Model for Efficient fMRI Acquisition
  10. ICLR 2025TD-Paint: Faster Diffusion Inpainting Through Time-Aware Pixel Conditioning
  11. ICLR 2025Test-Time Adaptation for Combating Missing Modalities in Egocentric Videos
  12. ICLR 2025Test-time Adaptation for Regression by Subspace Alignment
  13. ICLR 2025The Case for Cleaner Biosignals: High-fidelity Neural Compressor Enables Transfer from Cleaner iEEG to Noisier EEG
  14. ICLR 2025Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation Dynamics
  15. ICLR 2025Time After Time: Deep-Q Effect Estimation for Interventions on When and What to do
  16. ICLR 2025Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts
  17. ICLR 2025TimeInf: Time Series Data Contribution via Influence Functions
  18. ICLR 2025TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting
  19. ICLR 2025TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis
  20. ICLR 2025Timer-XL: Long-Context Transformers for Unified Time Series Forecasting
  21. ICLR 2025Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
  22. ICLR 2025Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders
  23. ICLR 2025Towards Neural Scaling Laws for Time Series Foundation Models
  24. ICLR 2025TRENDy: Temporal Regression of Effective Nonlinear Dynamics
  25. ICLR 2025TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series Forecasting
  26. ICLR 2025TSC-Net: Prediction of Pedestrian Trajectories by Trajectory-Scene-Cell Classification
  27. ICLR 2025TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi Diagram
  28. ICLR 2025TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation
  29. ICLR 2025Zero-shot Imputation with Foundation Inference Models for Dynamical Systems
  30. ICLR 2025Zero-shot Model-based Reinforcement Learning using Large Language Models
  31. ICML 2025$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
  32. ICML 2025A Closer Look at Transformers for Time Series Forecasting: Understanding Why They Work and Where They Struggle
  33. ICML 2025A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments
  34. ICML 2025A Non-isotropic Time Series Diffusion Model with Moving Average Transitions
  35. ICML 2025Active Learning with Selective Time-Step Acquisition for PDEs
  36. ICML 2025AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting
  37. ICML 2025AEQA-NAT : Adaptive End-to-end Quantization Alignment Training Framework for Non-autoregressive Machine Translation
  38. ICML 2025An Architecture Search Framework for Inference-Time Techniques
  39. ICML 2025An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions
  40. ICML 2025Anytime-Constrained Equilibria in Polynomial Time
  41. ICML 2025Arrow: Accelerator for Time Series Causal Discovery with Time Weaving
  42. ICML 2025Automatic Differentiation of Optimization Algorithms with Time-Varying Updates
  43. ICML 2025Bayesian Basis Function Approximation for Scalable Gaussian Process Priors in Deep Generative Models
  44. ICML 2025BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
  45. ICML 2025Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation
  46. ICML 2025Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
  47. ICML 2025BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling
  48. ICML 2025Calibrating Video Watch-time Predictions with Credible Prototype Alignment
  49. ICML 2025Categorical Schrödinger Bridge Matching
  50. ICML 2025Causal Discovery from Conditionally Stationary Time Series

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查时间序列在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "time-series"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「图与结构化数据」下的其他主题