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 230 篇，第 4 / 5 页

  1. ICLR 2025Scaling Long Context Training Data by Long-Distance Referrals
  2. ICLR 2025SCBench: A KV Cache-Centric Analysis of Long-Context Methods
  3. ICLR 2025Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning
  4. ICLR 2025Self-Updatable Large Language Models by Integrating Context into Model Parameters
  5. ICLR 2025TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting
  6. ICLR 2025Timer-XL: Long-Context Transformers for Unified Time Series Forecasting
  7. ICLR 2025Towards Learning High-Precision Least Squares Algorithms with Sequence Models
  8. ICLR 2025Training Free Exponential Context Extension via Cascading KV Cache
  9. ICLR 2025Transformers are Universal In-context Learners
  10. ICLR 2025Transformers Handle Endogeneity in In-Context Linear Regression
  11. ICLR 2025Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
  12. ICLR 2025Unsupervised Meta-Learning via In-Context Learning
  13. ICLR 2025Vector-ICL: In-context Learning with Continuous Vector Representations
  14. ICLR 2025VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning
  15. ICLR 2025Wavelet-based Positional Representation for Long Context
  16. ICLR 2025What is Wrong with Perplexity for Long-context Language Modeling?
  17. ICLR 2025Why Does the Effective Context Length of LLMs Fall Short?
  18. ICLR 2025Why In-Context Learning Models are Good Few-Shot Learners?
  19. ICLR 2025ZETA: Leveraging $Z$-order Curves for Efficient Top-$k$ Attention
  20. ICLR 2024A Benchmark for Learning to Translate a New Language from One Grammar Book
  21. ICLR 2024AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents
  22. ICLR 2024AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
  23. ICLR 2024BooookScore: A systematic exploration of book-length summarization in the era of LLMs
  24. ICLR 2024CausalLM is not optimal for in-context learning
  25. ICLR 2024CLEX: Continuous Length Extrapolation for Large Language Models
  26. ICLR 2024Compressed Context Memory for Online Language Model Interaction
  27. ICLR 2024Context is Environment
  28. ICLR 2024Context-Aware Meta-Learning
  29. ICLR 2024Equivariant Matrix Function Neural Networks
  30. ICLR 2024FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data
  31. ICLR 2024FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
  32. ICLR 2024Function Vectors in Large Language Models
  33. ICLR 2024Functional Interpolation for Relative Positions improves Long Context Transformers
  34. ICLR 2024Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
  35. ICLR 2024How do Language Models Bind Entities in Context?
  36. ICLR 2024HyperAttention: Long-context Attention in Near-Linear Time
  37. ICLR 2024IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
  38. ICLR 2024IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
  39. ICLR 2024In-context Autoencoder for Context Compression in a Large Language Model
  40. ICLR 2024In-Context Learning Learns Label Relationships but Is Not Conventional Learning
  41. ICLR 2024In-Context Learning through the Bayesian Prism
  42. ICLR 2024In-Context Pretraining: Language Modeling Beyond Document Boundaries
  43. ICLR 2024Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability
  44. ICLR 2024Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning
  45. ICLR 2024Language Modeling Is Compression
  46. ICLR 2024Long-tailed Diffusion Models with Oriented Calibration
  47. ICLR 2024LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
  48. ICLR 2024Looped Transformers are Better at Learning Learning Algorithms
  49. ICLR 2024MEND: Meta Demonstration Distillation for Efficient and Effective In-Context Learning
  50. ICLR 2024Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors

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