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

88 papers, page 1 of 2

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
29. ICLR 2025Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding
30. ICLR 2025BenTo: Benchmark Reduction with In-Context Transferability
31. ICLR 2025BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
32. ICLR 2025Can In-context Learning Really Generalize to Out-of-distribution Tasks?
33. ICLR 2025CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression
34. ICLR 2025Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
35. ICLR 2025DiffPC: Diffusion-based High Perceptual Fidelity Image Compression with Semantic Refinement
36. ICLR 2025ICLR: In-Context Learning of Representations
37. ICLR 2025Implicit In-context Learning
38. ICLR 2025Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency
39. ICLR 2025Learning Randomized Algorithms with Transformers
40. ICLR 2025Long Context Compression with Activation Beacon
41. ICLR 2025Lossy Compression with Pretrained Diffusion Models
42. ICLR 2025MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba
43. ICLR 2025MCNC: Manifold-Constrained Reparameterization for Neural Compression
44. ICLR 2025MELODI: Exploring Memory Compression for Long Contexts
45. ICLR 2025Metalic: Meta-Learning In-Context with Protein Language Models
46. ICLR 2025MoDeGPT: Modular Decomposition for Large Language Model Compression
47. ICLR 2025On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery
48. ICLR 2025Palu: KV-Cache Compression with Low-Rank Projection
49. ICLR 2025PICASO: Permutation-Invariant Context Composition with State Space Models
50. ICLR 2025RazorAttention: Efficient KV Cache Compression Through Retrieval Heads

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.