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 52 篇，第 1 / 2 页

  1. NeurIPS 2024[Re] CUDA: Curriculum of Data Augmentation for Long‐tailed Recognition
  2. NeurIPS 2024An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding
  3. NeurIPS 2024AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
  4. NeurIPS 2024BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack
  5. NeurIPS 2024Balancing Context Length and Mixing Times for Reinforcement Learning at Scale
  6. NeurIPS 2024Base of RoPE Bounds Context Length
  7. NeurIPS 2024BERTs are Generative In-Context Learners
  8. NeurIPS 2024DAPE: Data-Adaptive Positional Encoding for Length Extrapolation
  9. NeurIPS 2024Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
  10. NeurIPS 2024Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling
  11. NeurIPS 2024Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data
  12. NeurIPS 2024Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate
  13. NeurIPS 2024Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective
  14. NeurIPS 2024Exploring Context Window of Large Language Models via Decomposed Positional Vectors
  15. NeurIPS 2024Flexible Context-Driven Sensory Processing in Dynamical Vision Models
  16. NeurIPS 2024Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
  17. NeurIPS 2024Grammar-Aligned Decoding
  18. NeurIPS 2024In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
  19. NeurIPS 2024InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
  20. NeurIPS 2024KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
  21. NeurIPS 2024Learning Partitions from Context
  22. NeurIPS 2024Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models
  23. NeurIPS 2024Linear Transformers are Versatile In-Context Learners
  24. NeurIPS 2024Long-range Brain Graph Transformer
  25. NeurIPS 2024Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie Stimuli
  26. NeurIPS 2024Long-tailed Object Detection Pretraining: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction
  27. NeurIPS 2024LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
  28. NeurIPS 2024Make Your LLM Fully Utilize the Context
  29. NeurIPS 2024MambaLRP: Explaining Selective State Space Sequence Models
  30. NeurIPS 2024Many-Shot In-Context Learning
  31. NeurIPS 2024Many-shot Jailbreaking
  32. NeurIPS 2024Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
  33. NeurIPS 2024MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
  34. NeurIPS 2024Mini-Sequence Transformers: Optimizing Intermediate Memory for Long Sequences Training
  35. NeurIPS 2024Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
  36. NeurIPS 2024MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations
  37. NeurIPS 2024Needle In A Multimodal Haystack
  38. NeurIPS 2024Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs
  39. NeurIPS 2024One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
  40. NeurIPS 2024Opponent Modeling with In-context Search
  41. NeurIPS 2024Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context
  42. NeurIPS 2024Probing the Decision Boundaries of In-context Learning in Large Language Models
  43. NeurIPS 2024Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
  44. NeurIPS 2024Robust Sleep Staging over Incomplete Multimodal Physiological Signals via Contrastive Imagination
  45. NeurIPS 2024Selective Attention: Enhancing Transformer through Principled Context Control
  46. NeurIPS 2024StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses
  47. NeurIPS 2024Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack
  48. NeurIPS 2024The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
  49. NeurIPS 2024The GAN is dead; long live the GAN! A Modern GAN Baseline
  50. NeurIPS 2024Transformers are Minimax Optimal Nonparametric In-Context Learners

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