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 757 篇，第 10 / 16 页

  1. NeurIPS 2025Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
  2. NeurIPS 2025Rotary Masked Autoencoders are Versatile Learners
  3. NeurIPS 2025Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
  4. NeurIPS 2025Scalable Signature Kernel Computations via Local Neumann Series Expansions
  5. NeurIPS 2025Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching
  6. NeurIPS 2025Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
  7. NeurIPS 2025ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection
  8. NeurIPS 2025Searching Latent Program Spaces
  9. NeurIPS 2025Selective Learning for Deep Time Series Forecasting
  10. NeurIPS 2025Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly Detection
  11. NeurIPS 2025Semi-supervised Graph Anomaly Detection via Robust Homophily Learning
  12. NeurIPS 2025SEMPO: Lightweight Foundation Models for Time Series Forecasting
  13. NeurIPS 2025Sequence Modeling with Spectral Mean Flows
  14. NeurIPS 2025SGN: Shifted Window-Based Hierarchical Variable Grouping for Multivariate Time Series Classification
  15. NeurIPS 2025ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models
  16. NeurIPS 2025Single-Step Operator Learning for Conditioned Time-Series Diffusion Models
  17. NeurIPS 2025Sinusoidal Initialization, Time for a New Start
  18. NeurIPS 2025SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks
  19. NeurIPS 2025SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
  20. NeurIPS 2025STaRFormer: Semi-Supervised Task-Informed Representation Learning via Dynamic Attention-Based Regional Masking for Sequential Data
  21. NeurIPS 2025Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models
  22. NeurIPS 2025Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models
  23. NeurIPS 2025Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
  24. NeurIPS 2025Synthetic Series-Symbol Data Generation for Time Series Foundation Models
  25. NeurIPS 2025SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series
  26. NeurIPS 2025TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE
  27. NeurIPS 2025Test Time Scaling for Neural Processes
  28. NeurIPS 2025Test-Time Adaptation by Causal Trimming
  29. NeurIPS 2025Test3R: Learning to Reconstruct 3D at Test Time
  30. NeurIPS 2025The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning
  31. NeurIPS 2025The Dual Nature of Plasticity Loss in Deep Continual Learning: Dissection and Mitigation
  32. NeurIPS 2025The Emergence of Abstract Thought in Large Language Models Beyond Any Language
  33. NeurIPS 2025This Time is Different: An Observability Perspective on Time Series Foundation Models
  34. NeurIPS 2025TIDMAD: Time Series Dataset for Discovering Dark Matter with AI Denoising
  35. NeurIPS 2025Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning
  36. NeurIPS 2025Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach
  37. NeurIPS 2025Time-Embedded Algorithm Unrolling for Computational MRI
  38. NeurIPS 2025Time-Evolving Dynamical System for Learning Latent Representations of Mouse Visual Neural Activity
  39. NeurIPS 2025Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series
  40. NeurIPS 2025Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
  41. NeurIPS 2025TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting
  42. NeurIPS 2025TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting
  43. NeurIPS 2025TimeWak: Temporal Chained-Hashing Watermark for Time Series Data
  44. NeurIPS 2025TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop
  45. NeurIPS 2025TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
  46. NeurIPS 2025Titans: Learning to Memorize at Test Time
  47. NeurIPS 2025ToF-IP: Time-of-Flight Enhanced Sparse Inertial Poser for Real-time Human Motion Capture
  48. NeurIPS 2025Toward Interpretable Evaluation Measures for Time Series Segmentation
  49. NeurIPS 2025Toward Relative Positional Encoding in Spiking Transformers
  50. NeurIPS 2025Towards Accurate Time Series Forecasting via Implicit Decoding

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