长上下文论文趋势 2023–2026

长窗口建模

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 838 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

长上下文论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20231818151566
202452436021176
202598875317255
2026130829831341

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

全部长上下文论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 838 篇，第 16 / 17 页

  1. NeurIPS 2024Many-shot Jailbreaking
  2. NeurIPS 2024Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
  3. NeurIPS 2024MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
  4. NeurIPS 2024Mini-Sequence Transformers: Optimizing Intermediate Memory for Long Sequences Training
  5. NeurIPS 2024Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
  6. NeurIPS 2024MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations
  7. NeurIPS 2024Needle In A Multimodal Haystack
  8. NeurIPS 2024Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs
  9. NeurIPS 2024One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
  10. NeurIPS 2024Opponent Modeling with In-context Search
  11. NeurIPS 2024Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context
  12. NeurIPS 2024Probing the Decision Boundaries of In-context Learning in Large Language Models
  13. NeurIPS 2024Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
  14. NeurIPS 2024Robust Sleep Staging over Incomplete Multimodal Physiological Signals via Contrastive Imagination
  15. NeurIPS 2024Selective Attention: Enhancing Transformer through Principled Context Control
  16. NeurIPS 2024StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses
  17. NeurIPS 2024Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack
  18. NeurIPS 2024The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
  19. NeurIPS 2024The GAN is dead; long live the GAN! A Modern GAN Baseline
  20. NeurIPS 2024Transformers are Minimax Optimal Nonparametric In-Context Learners
  21. NeurIPS 2024Universal In-Context Approximation By Prompting Fully Recurrent Models
  22. NeurIPS 2024xLSTM: Extended Long Short-Term Memory
  23. CVPR 2023AutoAD: Movie Description in Context
  24. CVPR 2023Balancing Logit Variation for Long-Tailed Semantic Segmentation
  25. CVPR 2023Context De-Confounded Emotion Recognition
  26. CVPR 2023Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification
  27. CVPR 2023Images Speak in Images: A Generalist Painter for In-Context Visual Learning
  28. CVPR 2023Leveraging Temporal Context in Low Representational Power Regimes
  29. CVPR 2023Long-Term Visual Localization With Mobile Sensors
  30. CVPR 2023LSTFE-Net:Long Short-Term Feature Enhancement Network for Video Small Object Detection
  31. CVPR 2023MoLo: Motion-Augmented Long-Short Contrastive Learning for Few-Shot Action Recognition
  32. CVPR 2023No One Left Behind: Improving the Worst Categories in Long-Tailed Learning
  33. CVPR 2023Rethinking Image Super Resolution From Long-Tailed Distribution Learning Perspective
  34. CVPR 2023Selective Structured State-Spaces for Long-Form Video Understanding
  35. CVPR 2023Towards End-to-End Generative Modeling of Long Videos With Memory-Efficient Bidirectional Transformers
  36. CVPR 2023Towards Realistic Long-Tailed Semi-Supervised Learning: Consistency Is All You Need
  37. CVPR 2023Ultra-High Resolution Segmentation With Ultra-Rich Context: A Novel Benchmark
  38. ICLR 2023$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference
  39. ICLR 2023Artificial Neuronal Ensembles with Learned Context Dependent Gating
  40. ICLR 2023CUDA: Curriculum of Data Augmentation for Long-tailed Recognition
  41. ICLR 2023Decoupled Training for Long-Tailed Classification With Stochastic Representations
  42. ICLR 2023Delving into Semantic Scale Imbalance
  43. ICLR 2023Evaluating Long-Term Memory in 3D Mazes
  44. ICLR 2023Generate rather than Retrieve: Large Language Models are Strong Context Generators
  45. ICLR 2023In-context Reinforcement Learning with Algorithm Distillation
  46. ICLR 2023Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models
  47. ICLR 2023Long Range Language Modeling via Gated State Spaces
  48. ICLR 2023Long-Tailed Learning Requires Feature Learning
  49. ICLR 2023Long-Tailed Partial Label Learning via Dynamic Rebalancing
  50. ICLR 2023MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting

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 查长上下文在 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": "long-context"}

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长上下文论文？
共 838 篇，按年份分别是 2023 年 66 篇、2024 年 176 篇、2025 年 255 篇、2026 年 341 篇。
NeurIPS 2026 有多少篇长上下文论文？
NeurIPS 2026 有 130 篇长上下文论文，上一届是 98 篇。
ICLR 2026 有多少篇长上下文论文？
ICLR 2026 有 82 篇长上下文论文，上一届是 87 篇。
ICML 2026 有多少篇长上下文论文？
ICML 2026 有 98 篇长上下文论文，上一届是 53 篇。
CVPR 2026 有多少篇长上下文论文？
CVPR 2026 有 31 篇长上下文论文，上一届是 17 篇。
哪个会议的长上下文论文最多？
NeurIPS，2023–2026 年共 298 篇。

「长上下文与记忆」下的其他主题