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

109 papers, page 1 of 3

1. CVPR 2025CASP: Compression of Large Multimodal Models Based on Attention Sparsity
2. CVPR 2025ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression
3. CVPR 2025Embracing Collaboration Over Competition: Condensing Multiple Prompts for Visual In-Context Learning
4. CVPR 2025Fitted Neural Lossless Image Compression
5. CVPR 2025FLAVC: Learned Video Compression with Feature Level Attention
6. CVPR 2025GA3CE: Unconstrained 3D Gaze Estimation with Gaze-Aware 3D Context Encoding
7. CVPR 2025Learned Image Compression with Dictionary-based Entropy Model
8. CVPR 2025Linear Attention Modeling for Learned Image Compression
9. CVPR 2025Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues
10. CVPR 2025MambaIC: State Space Models for High-Performance Learned Image Compression
11. CVPR 2025Neural Video Compression with Context Modulation
12. CVPR 2025Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition
13. CVPR 2025OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels
14. CVPR 2025Perceptual Video Compression with Neural Wrapping
15. CVPR 2025Random Conditioning for Diffusion Model Compression with Distillation
16. CVPR 2025Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
17. CVPR 2025Temporal Action Detection Model Compression by Progressive Block Drop
18. CVPR 2025TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression
19. CVPR 2025VoCo-LLaMA: Towards Vision Compression with Large Language Models
20. ICLR 2025Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding
21. ICLR 2025BenTo: Benchmark Reduction with In-Context Transferability
22. ICLR 2025BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
23. ICLR 2025Can In-context Learning Really Generalize to Out-of-distribution Tasks?
24. ICLR 2025CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression
25. ICLR 2025Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
26. ICLR 2025DiffPC: Diffusion-based High Perceptual Fidelity Image Compression with Semantic Refinement
27. ICLR 2025ICLR: In-Context Learning of Representations
28. ICLR 2025Implicit In-context Learning
29. ICLR 2025Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency
30. ICLR 2025Learning Randomized Algorithms with Transformers
31. ICLR 2025Long Context Compression with Activation Beacon
32. ICLR 2025Lossy Compression with Pretrained Diffusion Models
33. ICLR 2025MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba
34. ICLR 2025MCNC: Manifold-Constrained Reparameterization for Neural Compression
35. ICLR 2025MELODI: Exploring Memory Compression for Long Contexts
36. ICLR 2025Metalic: Meta-Learning In-Context with Protein Language Models
37. ICLR 2025MoDeGPT: Modular Decomposition for Large Language Model Compression
38. ICLR 2025On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery
39. ICLR 2025Palu: KV-Cache Compression with Low-Rank Projection
40. ICLR 2025PICASO: Permutation-Invariant Context Composition with State Space Models
41. ICLR 2025RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
42. ICLR 2025ReAttention: Training-Free Infinite Context with Finite Attention Scope
43. ICLR 2025Rethinking Invariance in In-context Learning
44. ICLR 2025Streamlining Redundant Layers to Compress Large Language Models
45. ICLR 2025ThinK: Thinner Key Cache by Query-Driven Pruning
46. ICLR 2025Training Free Exponential Context Extension via Cascading KV Cache
47. ICLR 2025Transformers are Universal In-context Learners
48. ICLR 2025Unsupervised Meta-Learning via In-Context Learning
49. ICLR 2025Why Does the Effective Context Length of LLMs Fall Short?
50. ICLR 2025Why In-Context Learning Models are Good Few-Shot Learners?

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.