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 9 / 17 页

  1. ICLR 2025LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement
  2. ICLR 2025LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization
  3. ICLR 2025LongVILA: Scaling Long-Context Visual Language Models for Long Videos
  4. ICLR 2025LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
  5. ICLR 2025MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding
  6. ICLR 2025MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba
  7. ICLR 2025MELODI: Exploring Memory Compression for Long Contexts
  8. ICLR 2025Metalic: Meta-Learning In-Context with Protein Language Models
  9. ICLR 2025miniCTX: Neural Theorem Proving with (Long-)Contexts
  10. ICLR 2025Needle Threading: Can LLMs Follow Threads Through Near-Million-Scale Haystacks?
  11. ICLR 2025NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens
  12. ICLR 2025OmniKV: Dynamic Context Selection for Efficient Long-Context LLMs
  13. ICLR 2025On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery
  14. ICLR 2025Oscillatory State-Space Models
  15. ICLR 2025P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS
  16. ICLR 2025PEARL: Towards Permutation-Resilient LLMs
  17. ICLR 2025PICASO: Permutation-Invariant Context Composition with State Space Models
  18. ICLR 2025Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model
  19. ICLR 2025Radar: Fast Long-Context Decoding for Any Transformer
  20. ICLR 2025ReAttention: Training-Free Infinite Context with Finite Attention Scope
  21. ICLR 2025Rethinking Invariance in In-context Learning
  22. ICLR 2025Retrieval Head Mechanistically Explains Long-Context Factuality
  23. ICLR 2025RetroInText: A Multimodal Large Language Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation Learning
  24. ICLR 2025Revisiting In-context Learning Inference Circuit in Large Language Models
  25. ICLR 2025Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
  26. ICLR 2025Scaling Instruction-tuned LLMs to Million-token Contexts via Hierarchical Synthetic Data Generation
  27. ICLR 2025Scaling Long Context Training Data by Long-Distance Referrals
  28. ICLR 2025SCBench: A KV Cache-Centric Analysis of Long-Context Methods
  29. ICLR 2025Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning
  30. ICLR 2025Self-Updatable Large Language Models by Integrating Context into Model Parameters
  31. ICLR 2025TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting
  32. ICLR 2025Timer-XL: Long-Context Transformers for Unified Time Series Forecasting
  33. ICLR 2025Towards Learning High-Precision Least Squares Algorithms with Sequence Models
  34. ICLR 2025Training Free Exponential Context Extension via Cascading KV Cache
  35. ICLR 2025Transformers are Universal In-context Learners
  36. ICLR 2025Transformers Handle Endogeneity in In-Context Linear Regression
  37. ICLR 2025Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
  38. ICLR 2025Unsupervised Meta-Learning via In-Context Learning
  39. ICLR 2025Vector-ICL: In-context Learning with Continuous Vector Representations
  40. ICLR 2025VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning
  41. ICLR 2025Wavelet-based Positional Representation for Long Context
  42. ICLR 2025What is Wrong with Perplexity for Long-context Language Modeling?
  43. ICLR 2025Why Does the Effective Context Length of LLMs Fall Short?
  44. ICLR 2025Why In-Context Learning Models are Good Few-Shot Learners?
  45. ICLR 2025ZETA: Leveraging $Z$-order Curves for Efficient Top-$k$ Attention
  46. ICML 2025$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
  47. ICML 2025AdaSplash: Adaptive Sparse Flash Attention
  48. ICML 2025Advancing Personalized Learning with Neural Collapse for Long-Tail Challenge
  49. ICML 2025Behavioral Exploration: Learning to Explore via In-Context Adaptation
  50. ICML 2025Can Transformers Learn Full Bayesian Inference in Context?

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