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 28 篇，第 1 / 1 页

1. ICLR 2026An evolutionary perspective on modes of learning in Transformers
2. ICLR 2026ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
3. ICLR 2026Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
4. ICLR 2026COMI: Coarse-to-fine Context Compression via Marginal Information Gain
5. ICLR 2026Cut Less, Fold More: Model Compression through the Lens of Projection Geometry
6. ICLR 2026Draft-based Approximate Inference for LLMs
7. ICLR 2026EntropyLong: Effective Long-Context Training via Predictive Uncertainty
8. ICLR 2026Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding
9. ICLR 2026FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension
10. ICLR 2026From Markov to Laplace: How Mamba In-Context Learns Markov Chains
11. ICLR 2026In-Context Algorithm Emulation in Fixed-Weight Transformers
12. ICLR 2026Is In-Context Learning Learning?
13. ICLR 2026Learning is Forgetting; LLM Training As Lossy Compression
14. ICLR 2026Learning to Adapt: In-Context Learning Beyond Stationarity
15. ICLR 2026Long-Context Generalization with Sparse Attention
16. ICLR 2026Low-Latency Neural LiDAR Compression with 2D Context Models
17. ICLR 2026ProtoKV: Long-context Knowledges Are Already Well-Organized Before Your Query
18. ICLR 2026ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing
19. ICLR 2026Retrospective Sparse Attention for Efficient Long-Context Generation
20. ICLR 2026RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers
21. ICLR 2026Synchronizing Probabilities in Model-Driven Lossless Compression
22. ICLR 2026ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models
23. ICLR 2026To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration
24. ICLR 2026Tokenisation over Bounded Alphabets is Hard
25. ICLR 2026Transformers Learn Latent Mixture Models In-Context via Mirror Descent
26. ICLR 2026Unveiling Super Experts in Mixture-of-Experts Large Language Models
27. ICLR 2026VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
28. ICLR 2026Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis

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。