Context Compression papers, 2023–2026

Key findings

• Context Compression went from 39 papers in 2023 to 136 in 2026, roughly 3.5x in three years.
• NeurIPS publishes the most Context Compression work: 123 papers from 2023 to 2026, 34% of the four-venue total.
• The fastest-growing overlap is with Deep learning · large language models: papers tagged with both rose from 1 in 2023 to 13 in 2026.
• Among the 5 topics under Long Context and Memory, it ranks #4 by 2026 paper count; the fastest grower in the group, Retrieval Memory, is up 6.6x versus 3.5x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Context Compression papers

365 papers, page 4 of 8

151. CVPR 2025Random Conditioning for Diffusion Model Compression with Distillation
152. CVPR 2025Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
153. CVPR 2025Temporal Action Detection Model Compression by Progressive Block Drop
154. CVPR 2025TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression
155. CVPR 2025VoCo-LLaMA: Towards Vision Compression with Large Language Models
156. ICLR 2025Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding
157. ICLR 2025BenTo: Benchmark Reduction with In-Context Transferability
158. ICLR 2025BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
159. ICLR 2025Can In-context Learning Really Generalize to Out-of-distribution Tasks?
160. ICLR 2025CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression
161. ICLR 2025Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
162. ICLR 2025DiffPC: Diffusion-based High Perceptual Fidelity Image Compression with Semantic Refinement
163. ICLR 2025ICLR: In-Context Learning of Representations
164. ICLR 2025Implicit In-context Learning
165. ICLR 2025Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency
166. ICLR 2025Learning Randomized Algorithms with Transformers
167. ICLR 2025Long Context Compression with Activation Beacon
168. ICLR 2025Lossy Compression with Pretrained Diffusion Models
169. ICLR 2025MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba
170. ICLR 2025MCNC: Manifold-Constrained Reparameterization for Neural Compression
171. ICLR 2025MELODI: Exploring Memory Compression for Long Contexts
172. ICLR 2025Metalic: Meta-Learning In-Context with Protein Language Models
173. ICLR 2025MoDeGPT: Modular Decomposition for Large Language Model Compression
174. ICLR 2025On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery
175. ICLR 2025Palu: KV-Cache Compression with Low-Rank Projection
176. ICLR 2025PICASO: Permutation-Invariant Context Composition with State Space Models
177. ICLR 2025RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
178. ICLR 2025ReAttention: Training-Free Infinite Context with Finite Attention Scope
179. ICLR 2025Rethinking Invariance in In-context Learning
180. ICLR 2025Streamlining Redundant Layers to Compress Large Language Models
181. ICLR 2025ThinK: Thinner Key Cache by Query-Driven Pruning
182. ICLR 2025Training Free Exponential Context Extension via Cascading KV Cache
183. ICLR 2025Transformers are Universal In-context Learners
184. ICLR 2025Unsupervised Meta-Learning via In-Context Learning
185. ICLR 2025Why Does the Effective Context Length of LLMs Fall Short?
186. ICLR 2025Why In-Context Learning Models are Good Few-Shot Learners?
187. ICLR 2025You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning
188. ICML 2025CommVQ: Commutative Vector Quantization for KV Cache Compression
189. ICML 2025Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data
190. ICML 2025DLP: Dynamic Layerwise Pruning in Large Language Models
191. ICML 2025Does learning the right latent variables necessarily improve in-context learning?
192. ICML 2025Efficient LiDAR Reflectance Compression via Scanning Serialization
193. ICML 2025Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
194. ICML 2025EvoPress: Accurate Dynamic Model Compression via Evolutionary Search
195. ICML 2025In-Context Deep Learning via Transformer Models
196. ICML 2025In-Context Learning and Occam's Razor
197. ICML 2025Iterative Vectors: In-Context Gradient Steering without Backpropagation
198. ICML 2025Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary Points
199. ICML 2025Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries
200. ICML 2025NExtLong: Toward Effective Long-Context Training without Long Documents

FAQ

How many Context Compression papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

365 in total: 39 in 2023, 81 in 2024, 109 in 2025, 136 in 2026.

How many Context Compression papers are at NeurIPS 2026?

NeurIPS 2026 has 50 Context Compression papers, versus 38 the year before.

How many Context Compression papers are at ICLR 2026?

ICLR 2026 has 28 Context Compression papers, versus 32 the year before.

How many Context Compression papers are at ICML 2026?

ICML 2026 has 39 Context Compression papers, versus 20 the year before.

How many Context Compression papers are at CVPR 2026?

CVPR 2026 has 19 Context Compression papers, versus 19 the year before.

Which conference publishes the most Context Compression papers?

NeurIPS, with 123 papers from 2023 to 2026.