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 6 / 17 页

  1. NeurIPS 2026Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation
  2. NeurIPS 2026FFTSparse: Relative-Position Correlation Guided Sparse Attention for Long-Context Language Models
  3. NeurIPS 2026Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics
  4. NeurIPS 2026Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference
  5. NeurIPS 2026Fractional State Space Transition for Long Sequence Modeling
  6. NeurIPS 2026FrameScout: Scouting Query-Relevant Frames for Long Video Understanding
  7. NeurIPS 2026From History to State: Constant-Context Skill Learning for LLM Agents
  8. NeurIPS 2026From Label Priors to Task Evidence: Long-Video Frame Selection via Bayesian GRPO
  9. NeurIPS 2026GeneZip: Region-Aware Compression for Long Context DNA Modeling
  10. NeurIPS 2026Geometry Matters in Packed 3D Attention
  11. NeurIPS 2026Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing
  12. NeurIPS 2026Git Context Controller: Manage the Context of Agents by Agentic Git
  13. NeurIPS 2026Global Context Guidance for Diffusion Large Language Models
  14. NeurIPS 2026Heterogeneous Parallelism for Multimodal Large Language Model Training
  15. NeurIPS 2026Imitation Dominates Reinforcement: Direct In-Context RL Is Closer to ICL Than RL
  16. NeurIPS 2026Improving Context-Shift Robustness of Convolutional Networks via Context-Regularized Cross-Entropy
  17. NeurIPS 2026In-Context Benign Overfitting: A Feature-Selection Model in Linear Regression ICL
  18. NeurIPS 2026In-context learning to predict critical transitions in dynamical systems
  19. NeurIPS 2026Inadvertent Context Leakage in Language Models
  20. NeurIPS 2026Incremental Learning in Transformers for In-Context Associative Recall
  21. NeurIPS 2026Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
  22. NeurIPS 2026Know Where You Stand: Memory-Source Choice in Long-Context Dialogue Agents
  23. NeurIPS 2026KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs
  24. NeurIPS 2026Large Language Models Develop Belief State Geometry In-Context
  25. NeurIPS 2026Learning to Follow In-Context Watermark Instructions via Self-Distillation
  26. NeurIPS 2026Learning-to-Memorize: Dynamic Context Management for Long-Horizon Autoregressive Video Generation
  27. NeurIPS 2026Lemon: Evidence-Risk-Aware Adaptive Organization for Long-Horizon LLM Agents
  28. NeurIPS 2026LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
  29. NeurIPS 2026Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents
  30. NeurIPS 2026Logarithmic Depth Suffices for In-Context Gradient Descent
  31. NeurIPS 2026Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions
  32. NeurIPS 2026Long-Context Generation Is a Sampling Problem
  33. NeurIPS 2026Long-Context Language Models Require Extreme Sparsity in Context Dimension
  34. NeurIPS 2026Long-Horizon Agency Belongs in the Harness, Not the Context Window Only
  35. NeurIPS 2026Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities
  36. NeurIPS 2026Long-Term Risks of Risk-Based Allocation
  37. NeurIPS 2026LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE
  38. NeurIPS 2026Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction
  39. NeurIPS 2026MedHorizon: Towards Long-context Medical Video Understanding in the Wild
  40. NeurIPS 2026Motif-Mamba: network motif improved mamba for long-range sequence modeling
  41. NeurIPS 2026MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation
  42. NeurIPS 2026Neuromodulated Constrained Autoencoders for Context-Dependent Manifold Learning
  43. NeurIPS 2026NINJA: A Navigator–Inspector Joint Architecture for Context-Efficient Issue Localization
  44. NeurIPS 2026NOCE-Net: Representation Learning for Battery Operational Context via Nested Sequence Modelling
  45. NeurIPS 2026Not All Tokens Should Be Treated Equally: Context Credits Reassignment
  46. NeurIPS 2026OmniMemBench: Towards Scalable Evaluation of Long-Term Omni-Modal Agent Memory
  47. NeurIPS 2026On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models
  48. NeurIPS 2026Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand
  49. NeurIPS 2026PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
  50. NeurIPS 2026PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory

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