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

38 papers, page 1 of 1

1. NeurIPS 2025AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
2. NeurIPS 2025AttentionPredictor: Temporal Patterns Matter for KV Cache Compression
3. NeurIPS 2025Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression
4. NeurIPS 2025Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression
5. NeurIPS 2025ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
6. NeurIPS 2025COALA: Numerically Stable and Efficient Framework for Context-Aware Low-Rank Approximation
7. NeurIPS 2025Conditional Distribution Compression via the Kernel Conditional Mean Embedding
8. NeurIPS 2025Constant Bit-size Transformers Are Turing Complete
9. NeurIPS 2025DeepHalo: A Neural Choice Model with Controllable Context Effects
10. NeurIPS 2025Disentangling Latent Shifts of In-Context Learning with Weak Supervision
11. NeurIPS 2025Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention
12. NeurIPS 2025DUO: No Compromise to Accuracy Degradation
13. NeurIPS 2025Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference
14. NeurIPS 2025End-to-End Low-Light Enhancement for Object Detection with Learned Metadata from RAWs
15. NeurIPS 2025FP4 All the Way: Fully Quantized Training of Large Language Models
16. NeurIPS 2025From Softmax to Score: Transformers Can Effectively Implement In-Context Denoising Steps
17. NeurIPS 2025Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs
18. NeurIPS 2025In-Context Compositional Learning vis Sparse Coding Transformer
19. NeurIPS 2025InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
20. NeurIPS 2025KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments
21. NeurIPS 2025KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
22. NeurIPS 2025Language Models (Mostly) Know When to Stop Reading
23. NeurIPS 2025Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need
24. NeurIPS 2025LittleBit: Ultra Low-Bit Quantization via Latent Factorization
25. NeurIPS 2025MoRIC: A Modular Region-based Implicit Codec for Image Compression
26. NeurIPS 2025Neural Attention Search
27. NeurIPS 2025Neural B-frame Video Compression with Bi-directional Reference Harmonization
28. NeurIPS 2025Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention
29. NeurIPS 2025Scale-invariant attention
30. NeurIPS 2025SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference
31. NeurIPS 2025Stochastic Forward-Forward Learning through Representational Dimensionality Compression
32. NeurIPS 2025Theoretical Insights into In-context Learning with Unlabeled Data
33. NeurIPS 2025UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
34. NeurIPS 2025Unlabeled Data Can Provably Enhance In-Context Learning of Transformers
35. NeurIPS 2025Value-Guided KV Compression for LLMs via Approximated CUR Decomposition
36. NeurIPS 2025Vision-centric Token Compression in Large Language Model
37. NeurIPS 2025Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding
38. NeurIPS 2025zip2zip: Inference-Time Adaptive Tokenization via Online Compression

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.