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 599 篇，第 6 / 12 页

  1. ICML 2026TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction
  2. ICML 2026TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models
  3. ICML 2026Unfolded Laplacian Spectral Embedding: A Theoretically Grounded Approach to Dynamic Network Representation
  4. ICML 2026Unified Time Series Explanations via Amortized Optimization and Instance-level Multi-Expert Knowledge Distillation
  5. ICML 2026Universal Redundancies in Time Series Foundation Models
  6. ICML 2026WaveSSM: Multiscale State-Space Models for Non-stationary Signal Attention
  7. ICML 2026What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions
  8. ICML 2026What If We Allocate Test-Time Compute Adaptively?
  9. ICML 2026What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies
  10. ICML 2026WildCat: Near-Linear Attention in Theory and Practice
  11. ICML 2026Winformer: Transcending Pairwise Similarity for Time-series Generation
  12. ICML 2026Words Towards Explainability: Caption Label-Free Learning via Dual Loop Agentic Time Series Captioning
  13. ICML 2026ZeroDiff: Zero-Shot Time Series Reconstruction via Informed-Prior Diffusion
  14. ICML 2026Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis
  15. ICML 2025$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
  16. ICML 2025A Closer Look at Transformers for Time Series Forecasting: Understanding Why They Work and Where They Struggle
  17. ICML 2025A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments
  18. ICML 2025A Non-isotropic Time Series Diffusion Model with Moving Average Transitions
  19. ICML 2025Active Learning with Selective Time-Step Acquisition for PDEs
  20. ICML 2025AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting
  21. ICML 2025AEQA-NAT : Adaptive End-to-end Quantization Alignment Training Framework for Non-autoregressive Machine Translation
  22. ICML 2025An Architecture Search Framework for Inference-Time Techniques
  23. ICML 2025An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions
  24. ICML 2025Anytime-Constrained Equilibria in Polynomial Time
  25. ICML 2025Arrow: Accelerator for Time Series Causal Discovery with Time Weaving
  26. ICML 2025Automatic Differentiation of Optimization Algorithms with Time-Varying Updates
  27. ICML 2025Bayesian Basis Function Approximation for Scalable Gaussian Process Priors in Deep Generative Models
  28. ICML 2025BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
  29. ICML 2025Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation
  30. ICML 2025Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
  31. ICML 2025BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling
  32. ICML 2025Calibrating Video Watch-time Predictions with Credible Prototype Alignment
  33. ICML 2025Categorical Schrödinger Bridge Matching
  34. ICML 2025Causal Discovery from Conditionally Stationary Time Series
  35. ICML 2025Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection
  36. ICML 2025CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling
  37. ICML 2025Channel Normalization for Time Series Channel Identification
  38. ICML 2025CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations
  39. ICML 2025Conditional Diffusion Model with Nonlinear Data Transformation for Time Series Forecasting
  40. ICML 2025Conformal Anomaly Detection in Event Sequences
  41. ICML 2025Context is Key: A Benchmark for Forecasting with Essential Textual Information
  42. ICML 2025Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games
  43. ICML 2025Continuously Updating Digital Twins using Large Language Models
  44. ICML 2025Demeaned Sparse: Efficient Anomaly Detection by Residual Estimate
  45. ICML 2025Deterministic Sparse Fourier Transform for Continuous Signals with Frequency Gap
  46. ICML 2025Discovering Latent Causal Graphs from Spatiotemporal Data
  47. ICML 2025Discovering Physics Laws of Dynamical Systems via Invariant Function Learning
  48. ICML 2025Discrepancy Minimization in Input-Sparsity Time
  49. ICML 2025Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity
  50. ICML 2025Efficient Personalized Adaptation for Physiological Signal Foundation Model

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