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 365 篇，第 7 / 8 页

  1. NeurIPS 2024Causal Context Adjustment Loss for Learned Image Compression
  2. NeurIPS 2024ContextGS : Compact 3D Gaussian Splatting with Anchor Level Context Model
  3. NeurIPS 2024DiTFastAttn: Attention Compression for Diffusion Transformer Models
  4. NeurIPS 2024DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
  5. NeurIPS 2024Efficient Large Multi-modal Models via Visual Context Compression
  6. NeurIPS 2024Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective
  7. NeurIPS 2024ESPACE: Dimensionality Reduction of Activations for Model Compression
  8. NeurIPS 2024Euclidean distance compression via deep random features
  9. NeurIPS 2024Exploring Context Window of Large Language Models via Decomposed Positional Vectors
  10. NeurIPS 2024In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
  11. NeurIPS 2024KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
  12. NeurIPS 2024Learning Partitions from Context
  13. NeurIPS 2024MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
  14. NeurIPS 2024Make Your LLM Fully Utilize the Context
  15. NeurIPS 2024MeLLoC: Lossless Compression with High-order Mechanism Learning
  16. NeurIPS 2024MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
  17. NeurIPS 2024One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
  18. NeurIPS 2024Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding
  19. NeurIPS 2024S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning
  20. NeurIPS 2024SlimGPT: Layer-wise Structured Pruning for Large Language Models
  21. NeurIPS 2024SlimSAM: 0.1% Data Makes Segment Anything Slim
  22. NeurIPS 2024StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses
  23. NeurIPS 2024Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
  24. NeurIPS 2024Universal In-Context Approximation By Prompting Fully Recurrent Models
  25. NeurIPS 2024Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
  26. NeurIPS 2024xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
  27. CVPR 2023AutoAD: Movie Description in Context
  28. CVPR 2023Class-Incremental Exemplar Compression for Class-Incremental Learning
  29. CVPR 2023Context De-Confounded Emotion Recognition
  30. CVPR 2023Context-Based Trit-Plane Coding for Progressive Image Compression
  31. CVPR 2023Discriminator-Cooperated Feature Map Distillation for GAN Compression
  32. CVPR 2023Efficient Hierarchical Entropy Model for Learned Point Cloud Compression
  33. CVPR 2023Learned Image Compression With Mixed Transformer-CNN Architectures
  34. CVPR 2023Leveraging Temporal Context in Low Representational Power Regimes
  35. CVPR 2023Motion Information Propagation for Neural Video Compression
  36. CVPR 2023Neural Video Compression With Diverse Contexts
  37. CVPR 2023TINC: Tree-Structured Implicit Neural Compression
  38. CVPR 2023Ultra-High Resolution Segmentation With Ultra-Rich Context: A Novel Benchmark
  39. CVPR 2023Video Compression With Entropy-Constrained Neural Representations
  40. ICLR 2023$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference
  41. ICLR 2023A Unified Framework for Soft Threshold Pruning
  42. ICLR 2023Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats
  43. ICLR 2023Artificial Neuronal Ensembles with Learned Context Dependent Gating
  44. ICLR 2023CrAM: A Compression-Aware Minimizer
  45. ICLR 2023DFPC: Data flow driven pruning of coupled channels without data.
  46. ICLR 2023Generate rather than Retrieve: Large Language Models are Strong Context Generators
  47. ICLR 2023How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?
  48. ICLR 2023MIMT: Masked Image Modeling Transformer for Video Compression
  49. ICLR 2023Pruning Deep Neural Networks from a Sparsity Perspective
  50. ICLR 2023RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch

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