上下文压缩论文趋势 2023–2026

KV 压缩

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 365 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

上下文压缩论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202381351339
2024271533681
202538322019109
202650283919136

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

全部上下文压缩论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 123 篇，第 3 / 3 页

  1. NeurIPS 2024Learning Partitions from Context
  2. NeurIPS 2024MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
  3. NeurIPS 2024Make Your LLM Fully Utilize the Context
  4. NeurIPS 2024MeLLoC: Lossless Compression with High-order Mechanism Learning
  5. NeurIPS 2024MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
  6. NeurIPS 2024One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
  7. NeurIPS 2024Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding
  8. NeurIPS 2024S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning
  9. NeurIPS 2024SlimGPT: Layer-wise Structured Pruning for Large Language Models
  10. NeurIPS 2024SlimSAM: 0.1% Data Makes Segment Anything Slim
  11. NeurIPS 2024StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses
  12. NeurIPS 2024Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
  13. NeurIPS 2024Universal In-Context Approximation By Prompting Fully Recurrent Models
  14. NeurIPS 2024Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
  15. NeurIPS 2024xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
  16. NeurIPS 20232Direction: Theoretically Faster Distributed Training with Bidirectional Communication Compression
  17. NeurIPS 2023Do Not Marginalize Mechanisms, Rather Consolidate!
  18. NeurIPS 2023Idempotent Learned Image Compression with Right-Inverse
  19. NeurIPS 2023Meta-in-context learning in large language models
  20. NeurIPS 2023Private Distribution Learning with Public Data: The View from Sample Compression
  21. NeurIPS 2023PRODIGY: Enabling In-context Learning Over Graphs
  22. NeurIPS 2023Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
  23. NeurIPS 2023Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection

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 查上下文压缩在 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": "compression-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上下文压缩论文？
共 365 篇，按年份分别是 2023 年 39 篇、2024 年 81 篇、2025 年 109 篇、2026 年 136 篇。
NeurIPS 2026 有多少篇上下文压缩论文？
NeurIPS 2026 有 50 篇上下文压缩论文，上一届是 38 篇。
ICLR 2026 有多少篇上下文压缩论文？
ICLR 2026 有 28 篇上下文压缩论文，上一届是 32 篇。
ICML 2026 有多少篇上下文压缩论文？
ICML 2026 有 39 篇上下文压缩论文，上一届是 20 篇。
CVPR 2026 有多少篇上下文压缩论文？
CVPR 2026 有 19 篇上下文压缩论文，上一届是 19 篇。
哪个会议的上下文压缩论文最多？
NeurIPS，2023–2026 年共 123 篇。

「长上下文与记忆」下的其他主题