上下文压缩论文趋势 2023–2026

主要结论

• 上下文压缩论文从 2023 年的 39 篇增长到 2026 年的 136 篇，三年间扩大到约 3.5 倍。
• NeurIPS 是发上下文压缩论文最多的会议，2023–2026 年共 123 篇，占四个会议总量的 34%。
• 交叉方向里涨得最快的是深度学习 · large language models：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 13 篇。
• 在「长上下文与记忆」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的检索记忆是 6.6 倍，上下文压缩是 3.5 倍。

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

• NeurIPS 2026A Free Lunch in LLM Compression: Revisiting Retraining after Pruning
• ICML 2026A Unified Sparse Attention via Multi-Granularity Compression
• ICLR 2026An evolutionary perspective on modes of learning in Transformers
• CVPR 2026AstraNav-Memory Contexts Compression for Long Memory
• NeurIPS 2025AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
• ICML 2025Does learning the right latent variables necessarily improve in-context learning?
• ICLR 2025Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding
• CVPR 2025ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression
• NeurIPS 2024StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses
• ICML 2024Agnostic Sample Compression Schemes for Regression
• ICLR 2024Compressed Context Memory for Online Language Model Interaction
• CVPR 2024Diversity-aware Channel Pruning for StyleGAN Compression
• NeurIPS 2023Do Not Marginalize Mechanisms, Rather Consolidate!
• ICML 2023Private Federated Learning with Autotuned Compression
• ICLR 2023$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference
• CVPR 2023AutoAD: Movie Description in Context
• NeurIPS 2026A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
• ICML 2026Context-Driven Incremental Compression for Multi-Turn Dialogue Generation
• ICLR 2026Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
• CVPR 2026Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners

全部上下文压缩论文

共 57 篇，第 1 / 2 页

1. CVPR 2026ApET Approximation-Error Guided Token Compression for Efficient VLMs
2. CVPR 2026AstraNav-Memory Contexts Compression for Long Memory
3. CVPR 2026Block-based Learned Image Compression without Blocking Artifacts
4. CVPR 2026Common Inpainted Objects In-N-Out of Context
5. CVPR 2026DA-VAE Plug-in Latent Compression for Diffusion via Detail Alignment
6. CVPR 2026Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners
7. CVPR 2026FreqSIC Frequency-aware Stereo Image Compression with Bi-directional Checkerboard Context Model
8. CVPR 2026Generative Video Compression with One-Dimensional Latent Representation
9. CVPR 2026HiconAgent History Context-aware Policy Optimization for GUI Agents
10. CVPR 2026Hybrid Token Compression for Vision-Language Models
11. CVPR 2026INSID3 Training-Free In-Context Segmentation with DINOv3
12. CVPR 2026Meta-Learning In-Context Enables Training-Free Cross Subject Brain Decoding
13. CVPR 2026MuKV Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering
14. CVPR 2026Neural Dynamic GI Random-Access Neural Compression for Temporal Lightmaps in
15. CVPR 2026PR-MaGIC Prompt Refinement Via Mask Decoder Gradient Flow For In-Context
16. CVPR 2026Semantic Context Matters Improving Conditioning for Autoregressive Models
17. CVPR 2026Ultra-Fast Neural Video Compression
18. CVPR 2026VecAttention Vector-wise Sparse Attention for Accelerating Long Context Inference
19. CVPR 2026What Matters in Practical Learned Image Compression
20. CVPR 2025CASP: Compression of Large Multimodal Models Based on Attention Sparsity
21. CVPR 2025ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression
22. CVPR 2025Embracing Collaboration Over Competition: Condensing Multiple Prompts for Visual In-Context Learning
23. CVPR 2025Fitted Neural Lossless Image Compression
24. CVPR 2025FLAVC: Learned Video Compression with Feature Level Attention
25. CVPR 2025GA3CE: Unconstrained 3D Gaze Estimation with Gaze-Aware 3D Context Encoding
26. CVPR 2025Learned Image Compression with Dictionary-based Entropy Model
27. CVPR 2025Linear Attention Modeling for Learned Image Compression
28. CVPR 2025Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues
29. CVPR 2025MambaIC: State Space Models for High-Performance Learned Image Compression
30. CVPR 2025Neural Video Compression with Context Modulation
31. CVPR 2025Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition
32. CVPR 2025OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels
33. CVPR 2025Perceptual Video Compression with Neural Wrapping
34. CVPR 2025Random Conditioning for Diffusion Model Compression with Distillation
35. CVPR 2025Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
36. CVPR 2025Temporal Action Detection Model Compression by Progressive Block Drop
37. CVPR 2025TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression
38. CVPR 2025VoCo-LLaMA: Towards Vision Compression with Large Language Models
39. CVPR 2024Amodal Completion via Progressive Mixed Context Diffusion
40. CVPR 2024CLiC: Concept Learning in Context
41. CVPR 2024ContextSeg: Sketch Semantic Segmentation by Querying the Context with Attention
42. CVPR 2024Diversity-aware Channel Pruning for StyleGAN Compression
43. CVPR 2024In-Context Matting
44. CVPR 2024Learned Lossless Image Compression based on Bit Plane Slicing
45. CVPR 2023AutoAD: Movie Description in Context
46. CVPR 2023Class-Incremental Exemplar Compression for Class-Incremental Learning
47. CVPR 2023Context De-Confounded Emotion Recognition
48. CVPR 2023Context-Based Trit-Plane Coding for Progressive Image Compression
49. CVPR 2023Discriminator-Cooperated Feature Map Distillation for GAN Compression
50. CVPR 2023Efficient Hierarchical Entropy Model for Learned Point Cloud Compression

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。