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

97 papers, page 2 of 2

51. ICML 2025Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries
52. ICML 2025NExtLong: Toward Effective Long-Context Training without Long Documents
53. ICML 2025ParallelComp: Parallel Long-Context Compressor for Length Extrapolation
54. ICML 2025Prompt-based Depth Pruning of Large Language Models
55. ICML 2025Retraining-free Merging of Sparse MoE via Hierarchical Clustering
56. ICML 2025RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
57. ICML 2025SkipGPT: Each Token is One of a Kind
58. ICML 2025Training Dynamics of In-Context Learning in Linear Attention
59. ICML 2025Weight matrices compression based on PDB model in deep neural networks
60. ICML 2024Agnostic Sample Compression Schemes for Regression
61. ICML 2024An Information-Theoretic Analysis of In-Context Learning
62. ICML 2024Breaking through the learning plateaus of in-context learning in Transformer
63. ICML 2024Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks
64. ICML 2024Conditional Language Learning with Context
65. ICML 2024Data-free Neural Representation Compression with Riemannian Neural Dynamics
66. ICML 2024Debiased Distribution Compression
67. ICML 2024Dual Operating Modes of In-Context Learning
68. ICML 2024Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers
69. ICML 2024ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking
70. ICML 2024Extreme Compression of Large Language Models via Additive Quantization
71. ICML 2024Feedback Loops With Language Models Drive In-Context Reward Hacking
72. ICML 2024Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
73. ICML 2024How do Transformers Perform In-Context Autoregressive Learning ?
74. ICML 2024In-context Convergence of Transformers
75. ICML 2024In-Context Learning Agents Are Asymmetric Belief Updaters
76. ICML 2024In-context Learning on Function Classes Unveiled for Transformers
77. ICML 2024In-Context Principle Learning from Mistakes
78. ICML 2024In-Context Unlearning: Language Models as Few-Shot Unlearners
79. ICML 2024Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective
80. ICML 2024LLM Maybe LongLM: SelfExtend LLM Context Window Without Tuning
81. ICML 2024LoCoCo: Dropping In Convolutions for Long Context Compression
82. ICML 2024LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
83. ICML 2024LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models
84. ICML 2024Neural NeRF Compression
85. ICML 2024PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning
86. ICML 2024Position: Do pretrained Transformers Learn In-Context by Gradient Descent?
87. ICML 2024Rethinking Adversarial Robustness in the Context of the Right to be Forgotten
88. ICML 2024Training-Free Long-Context Scaling of Large Language Models
89. ICML 2024Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context
90. ICML 2024Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape
91. ICML 2024Why Larger Language Models Do In-context Learning Differently?
92. ICML 2024xT: Nested Tokenization for Larger Context in Large Images
93. ICML 2023Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming
94. ICML 2023Hardware-Aware Compression with Random Operation Access Specific Tile (ROAST) Hashing
95. ICML 2023Modality-Agnostic Variational Compression of Implicit Neural Representations
96. ICML 2023Private Federated Learning with Autotuned Compression
97. ICML 2023Transformers Learn In-Context by Gradient Descent

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.