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 2 / 17 页

  1. ICLR 2026Critical attention scaling in long-context transformers
  2. ICLR 2026Draft-based Approximate Inference for LLMs
  3. ICLR 2026DSSA: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation
  4. ICLR 2026ECHO: Toward Contextual Seq2Seq Paradigms in Large EEG Models
  5. ICLR 2026EntropyLong: Effective Long-Context Training via Predictive Uncertainty
  6. ICLR 2026Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding
  7. ICLR 2026Frayed RoPE and Long Inputs: A Geometric Perspective
  8. ICLR 2026FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension
  9. ICLR 2026From Collapse to Control: Understanding and Extending Context Length in Emerging Hybrid Models via Universal Position Interpolation
  10. ICLR 2026From Markov to Laplace: How Mamba In-Context Learns Markov Chains
  11. ICLR 2026FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel
  12. ICLR 2026Generative Diffusion Prior Distillation for Long-Context Knowledge Transfer
  13. ICLR 2026Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics
  14. ICLR 2026In-Context Algebra
  15. ICLR 2026In-Context Algorithm Emulation in Fixed-Weight Transformers
  16. ICLR 2026Inferring brain plasticity rule under long-term stimulation with structured recurrent dynamics
  17. ICLR 2026InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models
  18. ICLR 2026Intrinsic Entropy of Context Length Scaling in LLMs
  19. ICLR 2026Is In-Context Learning Learning?
  20. ICLR 2026IterResearch: Rethinking Long-Horizon Agents via Markovian State Reconstruction
  21. ICLR 2026Learning to Adapt: In-Context Learning Beyond Stationarity
  22. ICLR 2026Let's (not) just put things in Context: Test-time Training for Long-context LLMs
  23. ICLR 2026Long-Context Attention Benchmark: From Kernel Efficiency to Distributed Context Parallelism
  24. ICLR 2026Long-Context Generalization with Sparse Attention
  25. ICLR 2026Long-range Modeling and Processing of Multimodal Event Sequences
  26. ICLR 2026LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards
  27. ICLR 2026LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts
  28. ICLR 2026LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
  29. ICLR 2026MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
  30. ICLR 2026Mini-cluster Guided Long-tailed Deep Clustering
  31. ICLR 2026MMReD: a Cross-Modal Benchmark for Dense Context Reasoning
  32. ICLR 2026MrRoPE: Mixed-radix Rotary Position Embedding
  33. ICLR 2026On learning linear dynamical systems in context with attention layers
  34. ICLR 2026Out of the Memory Barrier: A Highly Memory-Efficient Training System for LLMs with Million-Token Contexts
  35. ICLR 2026PERK: Long-Context Reasoning as Parameter-Efficient Test-Time Learning
  36. ICLR 2026PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs
  37. ICLR 2026PMDformer: Patch-Mean Decoupling Transformer for Long-term Forecasting
  38. ICLR 2026ProtoKV: Long-context Knowledges Are Already Well-Organized Before Your Query
  39. ICLR 2026Queue Length Regret Bounds for Contextual Queueing Bandits
  40. ICLR 2026RACE Attention: A Strictly Linear-Time Attention for Long-Sequence Training
  41. ICLR 2026ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing
  42. ICLR 2026Retrospective Sparse Attention for Efficient Long-Context Generation
  43. ICLR 2026Revisiting Long-context Modeling from Context Denoising Perspective
  44. ICLR 2026Reward Is Enough: LLMs Are In-Context Reinforcement Learners
  45. ICLR 2026RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers
  46. ICLR 2026SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation
  47. ICLR 2026Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management
  48. ICLR 2026Short Window Attention Enables Long-Term Memorization
  49. ICLR 2026SinkTrack: Attention Sink based Context Anchoring for Large Language Models
  50. ICLR 2026Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Understanding

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