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 39 篇，第 1 / 1 页

1. CVPR 2023AutoAD: Movie Description in Context
2. CVPR 2023Class-Incremental Exemplar Compression for Class-Incremental Learning
3. CVPR 2023Context De-Confounded Emotion Recognition
4. CVPR 2023Context-Based Trit-Plane Coding for Progressive Image Compression
5. CVPR 2023Discriminator-Cooperated Feature Map Distillation for GAN Compression
6. CVPR 2023Efficient Hierarchical Entropy Model for Learned Point Cloud Compression
7. CVPR 2023Learned Image Compression With Mixed Transformer-CNN Architectures
8. CVPR 2023Leveraging Temporal Context in Low Representational Power Regimes
9. CVPR 2023Motion Information Propagation for Neural Video Compression
10. CVPR 2023Neural Video Compression With Diverse Contexts
11. CVPR 2023TINC: Tree-Structured Implicit Neural Compression
12. CVPR 2023Ultra-High Resolution Segmentation With Ultra-Rich Context: A Novel Benchmark
13. CVPR 2023Video Compression With Entropy-Constrained Neural Representations
14. ICLR 2023$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference
15. ICLR 2023A Unified Framework for Soft Threshold Pruning
16. ICLR 2023Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats
17. ICLR 2023Artificial Neuronal Ensembles with Learned Context Dependent Gating
18. ICLR 2023CrAM: A Compression-Aware Minimizer
19. ICLR 2023DFPC: Data flow driven pruning of coupled channels without data.
20. ICLR 2023Generate rather than Retrieve: Large Language Models are Strong Context Generators
21. ICLR 2023How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?
22. ICLR 2023MIMT: Masked Image Modeling Transformer for Video Compression
23. ICLR 2023Pruning Deep Neural Networks from a Sparsity Perspective
24. ICLR 2023RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
25. ICLR 2023TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning
26. ICLR 2023What learning algorithm is in-context learning? Investigations with linear models
27. ICML 2023Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming
28. ICML 2023Hardware-Aware Compression with Random Operation Access Specific Tile (ROAST) Hashing
29. ICML 2023Modality-Agnostic Variational Compression of Implicit Neural Representations
30. ICML 2023Private Federated Learning with Autotuned Compression
31. ICML 2023Transformers Learn In-Context by Gradient Descent
32. NeurIPS 20232Direction: Theoretically Faster Distributed Training with Bidirectional Communication Compression
33. NeurIPS 2023Do Not Marginalize Mechanisms, Rather Consolidate!
34. NeurIPS 2023Idempotent Learned Image Compression with Right-Inverse
35. NeurIPS 2023Meta-in-context learning in large language models
36. NeurIPS 2023Private Distribution Learning with Public Data: The View from Sample Compression
37. NeurIPS 2023PRODIGY: Enabling In-context Learning Over Graphs
38. NeurIPS 2023Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
39. NeurIPS 2023Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection

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。