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 298 篇，第 2 / 6 页

  1. NeurIPS 2026Coordinating Hundreds of RL Agents through Scalable Inference-Time Search
  2. NeurIPS 2026Counterfactual Explanations for Time-Series Classification via Constrained Flow Matching
  3. NeurIPS 2026Crosscoding Through Time: Sparse Feature Discovery Across Sequence Positions
  4. NeurIPS 2026CVTA: Cross-Variable Temporal Attention for Multivariate Irregular Time Series Prediction
  5. NeurIPS 2026Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation
  6. NeurIPS 2026Decomposing Temporal and Job-Induced Dynamics for Probabilistic Computing Workload Forecasting via Graph-Conditioned Dual-Branch Diffusion
  7. NeurIPS 2026DEDCA: Test-Time Adaptation for Generalized AI-Generated Image Detection
  8. NeurIPS 2026Deployment-Memory LLM Test-Time Training Should Require Behavioral Evidence Beyond Perplexity
  9. NeurIPS 2026Deployment-Time Online Imitation Learning from Corrective Demonstrations
  10. NeurIPS 2026DetectViT: Test-time Backdoor Detection for Vision Transformers via Inter-Head Attention Discrepancy
  11. NeurIPS 2026Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting
  12. NeurIPS 2026DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting
  13. NeurIPS 2026Diffusion-Time Concept Manifolds: Sparse Autoencoder Groups for Interpreting Denoising Language Models
  14. NeurIPS 2026Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
  15. NeurIPS 2026Distillation of Foundation Models for Time-dependent PDEs
  16. NeurIPS 2026Distilling Multi-Teacher Scoring Principles for Unsupervised Time Series Anomaly Detection
  17. NeurIPS 2026Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
  18. NeurIPS 2026DoFP-Aligned Lookup Tables for Real-Time Polarization Demosaicking
  19. NeurIPS 2026DSR-TSF: Spectrum-Driven Dynamic Routing for Efficient Long-Horizon Time Series Forecasting
  20. NeurIPS 2026DSSNet: Deep Spectral Structure Profiling Network for Traffic Flow Prediction
  21. NeurIPS 2026Dynamic Dual-Feedback Conformal Inference for Time Series Forecasting
  22. NeurIPS 2026Dynamic Tokenization via Reinforcement Patching: End-to-end Training and Zero-shot Transfer
  23. NeurIPS 2026DynaPFN: Zero-Shot Dynamical System Forecasting with Tabular Prior-Fitted Networks
  24. NeurIPS 2026Early Signals, Strong Decisions: Prefix-Guided Sampling for Parallel Test-Time Scaling
  25. NeurIPS 2026Echoes of Error: Residual-Directional Local Rollout Consistency for Timeseries Forecasting
  26. NeurIPS 2026Empowering Time Series Analysis with Large-Scale Multimodal Pretraining
  27. NeurIPS 2026Ensemble Modeling for Time Series Forecasting: an Adaptive Robust Optimization Approach
  28. NeurIPS 2026Entropy Guided Dynamic Patch Segmentation for Time Series Transformers
  29. NeurIPS 2026ESENSC: A Polynomial-Time Axiomatic Alternative to SHAP
  30. NeurIPS 2026EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample
  31. NeurIPS 2026Evaluating Deployable Inference-Time Error Prediction in Vision MoEs
  32. NeurIPS 2026Evaluating Uncertainty Calibration in Probabilistic Time Series Foundation Models
  33. NeurIPS 2026EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
  34. NeurIPS 2026Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics
  35. NeurIPS 2026ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
  36. NeurIPS 2026FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization
  37. NeurIPS 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?
  38. NeurIPS 2026FASTER: Rethinking Real-Time Flow VLAs
  39. NeurIPS 2026FENet: Functional Embedding Neural Network for Change-Point Detection in Functional Time Series
  40. NeurIPS 2026fev-bench: A Realistic Benchmark for Time Series Forecasting
  41. NeurIPS 2026Filter Banks: from Low-Rank Representations to Deep Models for Efficient Time Series Forecasting
  42. NeurIPS 2026FIND: Frequency Invariance Disentanglement for Test-Time Adaptation in LiDAR 3D Detection
  43. NeurIPS 2026Finite Time Analysis of Risk-Sensitive RL via Noisy Power Iteration
  44. NeurIPS 2026First-Token Attraction in Mamba Dynamics
  45. NeurIPS 2026FISC: Time-Series Forecasting via First-Layer Statistical Calibration Constraints
  46. NeurIPS 2026FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting
  47. NeurIPS 2026Flow Matching from Viewpoint of Proximal Operators
  48. NeurIPS 2026Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
  49. NeurIPS 2026Flow+Diff: Unifying Flow and Diffusion Representations for Multivariate Time Series Anomaly Detection
  50. NeurIPS 2026Focus, Align, and Diffuse: Time-Series-Aware Keyframe Diffusion for Cardiac Dynamic Synthesis from Sparse Observations

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