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 32 篇，第 1 / 1 页

1. ICLR 2025Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding
2. ICLR 2025BenTo: Benchmark Reduction with In-Context Transferability
3. ICLR 2025BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
4. ICLR 2025Can In-context Learning Really Generalize to Out-of-distribution Tasks?
5. ICLR 2025CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression
6. ICLR 2025Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
7. ICLR 2025DiffPC: Diffusion-based High Perceptual Fidelity Image Compression with Semantic Refinement
8. ICLR 2025ICLR: In-Context Learning of Representations
9. ICLR 2025Implicit In-context Learning
10. ICLR 2025Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency
11. ICLR 2025Learning Randomized Algorithms with Transformers
12. ICLR 2025Long Context Compression with Activation Beacon
13. ICLR 2025Lossy Compression with Pretrained Diffusion Models
14. ICLR 2025MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba
15. ICLR 2025MCNC: Manifold-Constrained Reparameterization for Neural Compression
16. ICLR 2025MELODI: Exploring Memory Compression for Long Contexts
17. ICLR 2025Metalic: Meta-Learning In-Context with Protein Language Models
18. ICLR 2025MoDeGPT: Modular Decomposition for Large Language Model Compression
19. ICLR 2025On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery
20. ICLR 2025Palu: KV-Cache Compression with Low-Rank Projection
21. ICLR 2025PICASO: Permutation-Invariant Context Composition with State Space Models
22. ICLR 2025RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
23. ICLR 2025ReAttention: Training-Free Infinite Context with Finite Attention Scope
24. ICLR 2025Rethinking Invariance in In-context Learning
25. ICLR 2025Streamlining Redundant Layers to Compress Large Language Models
26. ICLR 2025ThinK: Thinner Key Cache by Query-Driven Pruning
27. ICLR 2025Training Free Exponential Context Extension via Cascading KV Cache
28. ICLR 2025Transformers are Universal In-context Learners
29. ICLR 2025Unsupervised Meta-Learning via In-Context Learning
30. ICLR 2025Why Does the Effective Context Length of LLMs Fall Short?
31. ICLR 2025Why In-Context Learning Models are Good Few-Shot Learners?
32. ICLR 2025You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning

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。