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 585 篇，第 11 / 12 页

  1. NeurIPS 2025PhysDiff: A Physically-Guided Diffusion Model for Multivariate Time Series Anomaly Detection
  2. NeurIPS 2025Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers
  3. NeurIPS 2025PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series in Typhoon Forecasting
  4. NeurIPS 2025PMLF: A Physics-Guided Multiscale Loss Framework for Structurally Heterogeneous Time Series
  5. NeurIPS 2025POCO: Scalable Neural Forecasting through Population Conditioning
  6. NeurIPS 2025PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion
  7. NeurIPS 2025Pool Me Wisely: On the Effect of Pooling in Transformer-Based Models
  8. NeurIPS 2025Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
  9. NeurIPS 2025Provable Scaling Laws for the Test-Time Compute of Large Language Models
  10. NeurIPS 2025Quantifying Statistical Significance of Deep Nearest Neighbor Anomaly Detection via Selective Inference
  11. NeurIPS 2025Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detection
  12. NeurIPS 2025Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos
  13. NeurIPS 2025Redundancy-Aware Test-Time Graph Out-of-Distribution Detection
  14. NeurIPS 2025Remasking Discrete Diffusion Models with Inference-Time Scaling
  15. NeurIPS 2025Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning
  16. NeurIPS 2025Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling
  17. NeurIPS 2025Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
  18. NeurIPS 2025Rotary Masked Autoencoders are Versatile Learners
  19. NeurIPS 2025Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
  20. NeurIPS 2025Scalable Signature Kernel Computations via Local Neumann Series Expansions
  21. NeurIPS 2025Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching
  22. NeurIPS 2025Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
  23. NeurIPS 2025ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection
  24. NeurIPS 2025Searching Latent Program Spaces
  25. NeurIPS 2025Selective Learning for Deep Time Series Forecasting
  26. NeurIPS 2025Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly Detection
  27. NeurIPS 2025Semi-supervised Graph Anomaly Detection via Robust Homophily Learning
  28. NeurIPS 2025SEMPO: Lightweight Foundation Models for Time Series Forecasting
  29. NeurIPS 2025Sequence Modeling with Spectral Mean Flows
  30. NeurIPS 2025SGN: Shifted Window-Based Hierarchical Variable Grouping for Multivariate Time Series Classification
  31. NeurIPS 2025ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models
  32. NeurIPS 2025Single-Step Operator Learning for Conditioned Time-Series Diffusion Models
  33. NeurIPS 2025Sinusoidal Initialization, Time for a New Start
  34. NeurIPS 2025SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks
  35. NeurIPS 2025SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
  36. NeurIPS 2025STaRFormer: Semi-Supervised Task-Informed Representation Learning via Dynamic Attention-Based Regional Masking for Sequential Data
  37. NeurIPS 2025Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models
  38. NeurIPS 2025Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models
  39. NeurIPS 2025Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
  40. NeurIPS 2025Synthetic Series-Symbol Data Generation for Time Series Foundation Models
  41. NeurIPS 2025SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series
  42. NeurIPS 2025TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE
  43. NeurIPS 2025Test Time Scaling for Neural Processes
  44. NeurIPS 2025Test-Time Adaptation by Causal Trimming
  45. NeurIPS 2025Test3R: Learning to Reconstruct 3D at Test Time
  46. NeurIPS 2025The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning
  47. NeurIPS 2025The Dual Nature of Plasticity Loss in Deep Continual Learning: Dissection and Mitigation
  48. NeurIPS 2025The Emergence of Abstract Thought in Large Language Models Beyond Any Language
  49. NeurIPS 2025This Time is Different: An Observability Perspective on Time Series Foundation Models
  50. NeurIPS 2025TIDMAD: Time Series Dataset for Discovering Dark Matter with AI Denoising

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