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
- 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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 8 | 13 | 5 | 13 | 39 |
| 2024 | 27 | 15 | 33 | 6 | 81 |
| 2025 | 38 | 32 | 20 | 19 | 109 |
| 2026 | 50 | 28 | 39 | 19 | 136 |
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 365 篇，第 6 / 8 页
- CVPR 2024Learned Lossless Image Compression based on Bit Plane Slicing
- ICLR 2024ACRF: Compressing Explicit Neural Radiance Fields via Attribute Compression
- ICLR 2024CausalLM is not optimal for in-context learning
- ICLR 2024Compressed Context Memory for Online Language Model Interaction
- ICLR 2024Context is Environment
- ICLR 2024Context-Aware Meta-Learning
- ICLR 2024How do Language Models Bind Entities in Context?
- ICLR 2024HyperAttention: Long-context Attention in Near-Linear Time
- ICLR 2024IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
- ICLR 2024In defense of parameter sharing for model-compression
- ICLR 2024In-context Autoencoder for Context Compression in a Large Language Model
- ICLR 2024In-Context Learning Learns Label Relationships but Is Not Conventional Learning
- ICLR 2024Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression
- ICLR 2024Language Modeling Is Compression
- ICLR 2024RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation
- ICLR 2024Towards image compression with perfect realism at ultra-low bitrates
- ICML 2024Agnostic Sample Compression Schemes for Regression
- ICML 2024An Information-Theoretic Analysis of In-Context Learning
- ICML 2024Breaking through the learning plateaus of in-context learning in Transformer
- ICML 2024Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks
- ICML 2024Conditional Language Learning with Context
- ICML 2024Data-free Neural Representation Compression with Riemannian Neural Dynamics
- ICML 2024Debiased Distribution Compression
- ICML 2024Dual Operating Modes of In-Context Learning
- ICML 2024Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers
- ICML 2024ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking
- ICML 2024Extreme Compression of Large Language Models via Additive Quantization
- ICML 2024Feedback Loops With Language Models Drive In-Context Reward Hacking
- ICML 2024Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
- ICML 2024How do Transformers Perform In-Context Autoregressive Learning ?
- ICML 2024In-context Convergence of Transformers
- ICML 2024In-Context Learning Agents Are Asymmetric Belief Updaters
- ICML 2024In-context Learning on Function Classes Unveiled for Transformers
- ICML 2024In-Context Principle Learning from Mistakes
- ICML 2024In-Context Unlearning: Language Models as Few-Shot Unlearners
- ICML 2024Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective
- ICML 2024LLM Maybe LongLM: SelfExtend LLM Context Window Without Tuning
- ICML 2024LoCoCo: Dropping In Convolutions for Long Context Compression
- ICML 2024LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
- ICML 2024LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models
- ICML 2024Neural NeRF Compression
- ICML 2024PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning
- ICML 2024Position: Do pretrained Transformers Learn In-Context by Gradient Descent?
- ICML 2024Rethinking Adversarial Robustness in the Context of the Right to be Forgotten
- ICML 2024Training-Free Long-Context Scaling of Large Language Models
- ICML 2024Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context
- ICML 2024Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape
- ICML 2024Why Larger Language Models Do In-context Learning Differently?
- ICML 2024xT: Nested Tokenization for Larger Context in Large Images
- NeurIPS 2024Base of RoPE Bounds Context Length
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"}
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。