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 32 / 44 页

  1. ICLR 2024Explaining Time Series via Contrastive and Locally Sparse Perturbations
  2. ICLR 2024Exploring Diffusion Time-steps for Unsupervised Representation Learning
  3. ICLR 2024Feature-aligned N-BEATS with Sinkhorn divergence
  4. ICLR 2024Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
  5. ICLR 2024FITS: Modeling Time Series with $10k$ Parameters
  6. ICLR 2024FreeDyG: Frequency Enhanced Continuous-Time Dynamic Graph Model for Link Prediction
  7. ICLR 2024GAFormer: Enhancing Timeseries Transformers Through Group-Aware Embeddings
  8. ICLR 2024Generative Learning for Financial Time Series with Irregular and Scale-Invariant Patterns
  9. ICLR 2024Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs
  10. ICLR 2024Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations
  11. ICLR 2024HyperAttention: Long-context Attention in Near-Linear Time
  12. ICLR 2024IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
  13. ICLR 2024Incentive-Aware Federated Learning with Training-Time Model Rewards
  14. ICLR 2024Inherently Interpretable Time Series Classification via Multiple Instance Learning
  15. ICLR 2024Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series Prediction
  16. ICLR 2024iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
  17. ICLR 2024Language Models Represent Space and Time
  18. ICLR 2024Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time
  19. ICLR 2024Learning invariant representations of time-homogeneous stochastic dynamical systems
  20. ICLR 2024Learning to Embed Time Series Patches Independently
  21. ICLR 2024Let's do the time-warp-attend: Learning topological invariants of dynamical systems
  22. ICLR 2024Leveraging Generative Models for Unsupervised Alignment of Neural Time Series Data
  23. ICLR 2024Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time
  24. ICLR 2024LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition
  25. ICLR 2024MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods
  26. ICLR 2024MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process
  27. ICLR 2024ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis
  28. ICLR 2024MOTOR: A Time-to-Event Foundation Model For Structured Medical Records
  29. ICLR 2024Multi-Resolution Diffusion Models for Time Series Forecasting
  30. ICLR 2024NECO: NEural Collapse Based Out-of-distribution detection
  31. ICLR 2024On Diffusion Modeling for Anomaly Detection
  32. ICLR 2024On the Generalization and Approximation Capacities of Neural Controlled Differential Equations
  33. ICLR 2024Online GNN Evaluation Under Test-time Graph Distribution Shifts
  34. ICLR 2024Parametric Augmentation for Time Series Contrastive Learning
  35. ICLR 2024Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting
  36. ICLR 2024Periodicity Decoupling Framework for Long-term Series Forecasting
  37. ICLR 2024Polynormer: Polynomial-Expressive Graph Transformer in Linear Time
  38. ICLR 2024PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation
  39. ICLR 2024REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning
  40. ICLR 2024Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning
  41. ICLR 2024Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
  42. ICLR 2024RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies
  43. ICLR 2024Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement
  44. ICLR 2024Self-Supervised Contrastive Learning for Long-term Forecasting
  45. ICLR 2024SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations
  46. ICLR 2024SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series
  47. ICLR 2024Soft Contrastive Learning for Time Series
  48. ICLR 2024Stabilizing Backpropagation Through Time to Learn Complex Physics
  49. ICLR 2024Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data
  50. ICLR 2024STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction

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