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 16 / 44 页

  1. NeurIPS 2026Paloma: Phase-Conditioned Residual Modulation for Time Series Forecasting
  2. NeurIPS 2026PAMod: Modeling Cyclical Shifts via Phase-Amplitude Modulation for Non-stationary Time Series Forecasting
  3. NeurIPS 2026PhyTS: A Benchmark for Scientific Time Series
  4. NeurIPS 2026Polynomial-Time Algorithm for Thiele Voting Rules with Voter Interval Preferences
  5. NeurIPS 2026Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals
  6. NeurIPS 2026Position: Robust Reasoning Requires Internal Time, Not Scale Alone
  7. NeurIPS 2026Precision-Pyramid: Towards real-time neural decoding for fault-tolerant quantum computing
  8. NeurIPS 2026Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series
  9. NeurIPS 2026Prior as Geometry, Not Generator: Weak-Diffusion Test-Time Reconstruction for Dynamic MRI
  10. NeurIPS 2026PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
  11. NeurIPS 2026Problem-Dependent Dynamic Regret over a Predictor Class with One-Gradient Feedback
  12. NeurIPS 2026ProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputation
  13. NeurIPS 2026Progressive Memory Transformer: Memory-Aware Attention for Time-Series
  14. NeurIPS 2026Prompt–Activation Duality: Improving Activation Steering via Attention-Level Interventions
  15. NeurIPS 2026Proper Agnostic Learning of Functions of Halfspaces
  16. NeurIPS 2026Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks
  17. NeurIPS 2026Provable Test-Time Scaling for Beam Search in LLM Reasoning
  18. NeurIPS 2026ProxySearch: Decoupled Inference-Time Scaling for Diffusion Models via Asymmetric Noise-Rank Transfer
  19. NeurIPS 2026QWaveNet: Quantum-Enhanced Wavelet Network for Time Series Forecasting
  20. NeurIPS 2026Raw-Routed Mixture of Adapters: A Causal Intervention for Routing Collapse in Time Series Foundation Models
  21. NeurIPS 2026Reference-Guided Training: Adaptive Gradient Scaling via Per-Sample Loss Comparisons
  22. NeurIPS 2026Resolving Time-Frequency Ridge Crossings via Frequency-Rate Lifting
  23. NeurIPS 2026Response Time Enhances Alignment with Heterogeneous Preferences
  24. NeurIPS 2026Rethinking Expressivity and Efficiency in Test-Time Training
  25. NeurIPS 2026Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting
  26. NeurIPS 2026Rethinking Time Series Tokenization from a Frequency Perspective
  27. NeurIPS 2026Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection
  28. NeurIPS 2026RnR: a meta-solver for causal discovery in undersampled time series data
  29. NeurIPS 2026Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization
  30. NeurIPS 2026Robust Residual Correction via Selective Deployment for Time Series Forecasting
  31. NeurIPS 2026Robust Stream Classification using Time Neutralising Decision Trees
  32. NeurIPS 2026Rubato: Signature Attention for Irregular Multivariate Time Series Forecasting
  33. NeurIPS 2026Runtime Analysis of Cartesian Genetic Programming on MAX: A Proven Exponential Speedup
  34. NeurIPS 2026S3Former: Sequential, Structural, and Statistical Fusion for Continuous-Time Dynamic Graphs
  35. NeurIPS 2026Safe Active Learning with Future Viability Guarantees in Time-Series Models
  36. NeurIPS 2026SDFlow: Similarity-Driven Flow Matching for Time Series Generation
  37. NeurIPS 2026SDHilb: Schrödinger Dynamics-Guided Neural Network with Adaptive Multi-Scale Hilbert Transform for Time Series Forecasting
  38. NeurIPS 2026Self-Trained Verification for Training- and Test-Time Self-Improvement
  39. NeurIPS 2026Semantically Complementary Spectral Views Learning for Graph-Level Anomaly Detection
  40. NeurIPS 2026SetAD: Semi-Supervised Anomaly Learning in Contextual Sets
  41. NeurIPS 2026SIGMA: A Sigmoid-Gated Sampler for Test-Time Scaling in Diffusion Language Models
  42. NeurIPS 2026SLiDE: Structured Linear Dynamics for Forecasting with Exogenous Inputs
  43. NeurIPS 2026SPECS: Faster Test-Time Scaling through Speculative Drafts and Dynamic Switching
  44. NeurIPS 2026Spectral Energy Allocation Enables Source-Free Domain Adaptation in Time Series Forecasting
  45. NeurIPS 2026Spectral Transformer Neural Processes
  46. NeurIPS 2026Spikes as Detectors: Phase-Conditioned Spiking Dynamics for Time-Series Anomaly Detection
  47. NeurIPS 2026SpikeSTAG: A Dendritic Compartmental Spiking Graph Network for Multivariate Time-Series Forecasting
  48. NeurIPS 2026Stability-Weighted Direction Regularization Disentangles Generator Shortcuts from Detection Signal
  49. NeurIPS 2026Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping
  50. NeurIPS 2026Stable Alpha: Adversarial Invariant Representation Learning for Nonlinear Asset Pricing under Temporal Distribution Shifts

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