Large Language Model Compression

Ask about this topic

Recent momentum

-42%

11 papers in the last 28 days · 0.3% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Also in Token Compression

Neighbouring directions

Model and Context CompressionToken Compression

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

4 new papers

A weekly snapshot of new work published in Large Language Model Compression.

Period ending 2026-09-07

6 new papers

A weekly snapshot of new work published in Large Language Model Compression.

145 papers

Latest in Large Language Model Compression

Open your feed →
CardsList

  1. Per-Matrix Optimality Is Not Enough: Three-Level Optimization for Low-Rank LLM Compression

    Sep 14, 2026Huicheng Zhang, Xiyao Feng, Ze-Tong Li +6Large Language Model CompressionLanguage Model Perplexity

  2. Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models

    Sep 14, 2026Zhongzhan Huang, Junxin Li, Guoming Ling +3Large Language Model BenchmarksLarge Language Model Compression

  3. ESTS at WMT26: Routing-Informed Expert Pruning for Model Compression

    Sep 14, 2026Liu O. Martin, Lucas Bandarkar, Nanyun PengLarge Language Model CompressionMachine Translation Quality

  4. X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

    Sep 12, 2026Haojun Zhang, Yi Zou, Min Chen +7Large Audio Language ModelsAudio Encoders

  5. LILA: Calibration-Free Structured Pruning of Large Language Models via Latent Spectral Geometry

    Sep 11, 2026Sankar Behera, Dhruv Singh, Anshika Agnihotri +3Large Language Model CompressionStructured Pruning

  6. Forward-Free LLM Depth Pruning via Weight Redundancy

    Sep 9, 2026Vincent-Daniel Yun, Woosang LimMagnitude-Based PruningLarge Language Model Compression

  7. SGD-KV: Summarization Guided KV Cache Compression

    Sep 3, 2026Zeyu Liu, Woomin Song, Xuandi Fu +5Key-Value Cache CompressionEfficient Long-Context Inference

  8. Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone Distillation

    Sep 2, 2026Wenhui Chen, Zhifeng Li, Jie Zhou +5Confidence-Gated Closed-Loop Distillation FrameworkLarge Language Model Compression

  9. LatentPress: Context Compression Beyond Text and Vision

    Sep 1, 2026Zhengze Zhou, Hejian SangLarge Language Model CompressionModel and Context Compression

  10. Residual Sparsification via Output Importance for Compressing Mixture-of-Experts LLMs

    Sep 1, 2026Seungwoo Jung, Dohyeok Kwon, Seungmin Cha +4Large Language Model CompressionSparsity

  11. TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories

    Aug 31, 2026Daniel Agyei Asante, Yang LiLarge Language Model CompressionEfficient Long-Context Inference

  12. LaMoC: Loss-Aware Modular Compression for LLMs

    Aug 31, 2026Mohanad Odema, Jacob SongLarge Language Model CompressionModel and Context Compression

  13. Budget-Aware Compression Pipeline for Single-GPU LLM Inference: Methods, Trade-offs, and Coupling Effects

    Aug 30, 2026Hongyu Yu, Yifei ShenLarge Language Model CompressionLLM Inference Efficiency

  14. Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer Evidence

    Aug 30, 2026Mohammadali Khodabandehlou, Bhaskar KrishnamachariLarge Language Model CompressionLLM Inference Efficiency

  15. LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation

    Aug 13, 2026Dongfang Li, Zixuan Liu, Junmai Wang +5Biological MemoryLarge Language Model Agents

  16. Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization

    Aug 13, 2026Palaash Goel, Ayan Sengupta, Akshay Nambi +1Large Language Model CompressionStructured Pruning

  17. LegoLM: Structured Weight Sharing for Large Language Models

    Aug 9, 2026Joseph BinghamLarge Language Model CompressionLarge Language Model Scale

  18. Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs

    Aug 9, 2026Mohanad Odema, Gabrielle De Micheli, Dayin Gou +3Large Language Model CompressionLow-Rank Factorization

  19. Shape Mutating Expert Compression:LorExperts and BTExperts

    Aug 7, 2026Inesh Chakrabarti, Sourjya Roy, Bowen Bao +3Skewed Expert DemandExperts

  20. Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models

    Aug 7, 2026Minseok Kang, Hyunwoo Kim, Chanyoung Kim +3Large Language Model CompressionSparsity

  21. FraQ: Efficient Coordinate-Space Recompression for Federated Low-Rank Adaptation

    Aug 4, 2026Shenghui Li, Thiemo VoigtFederated Fine-TuningLarge Language Model Compression

  22. Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study

    Aug 4, 2026Ahmed Amine Aliane, Nasredine Semmar, Hassina AlianeMachine Translation QualityLarge Language Model Compression

  23. Diffuse to Compress: Leveraging Diffusion LMs for Lossless Compression

    Aug 4, 2026Angelo Nardone, Paolo FerraginaLarge Language Model CompressionModel and Context Compression

  24. When Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning

    Aug 3, 2026Andrew ZhangLarge Language Model CompressionModel and Context Compression

  25. AnchorKV: Anchor-Residual KV Cache Compression

    Aug 3, 2026Malik Khalaf, Yara Shamshoum, Nitzan Hodos +2Key-Value Cache CompressionKey-Value Cache

  26. Messages, Not Tokens: Grounded Coresets for Faithful VLM Compression

    Aug 3, 2026Long Qian, Jiaqi Wei, Bingke Zhu +2Large Language Model CompressionModel and Context Compression

  27. S^4R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching

    Aug 1, 2026Jialong Han, You Wu, Kewei TuKey-Value Cache CompressionKey-Value Cache

  28. F-WANDA: Fisher-Reweighted Post-Training Pruning for Sustainable Deployment of Large Language Models

    Aug 1, 2026Himanshu MishraLarge Language Model CompressionMagnitude-Based Pruning

  29. Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors

    Jul 28, 2026Jianfei Ma, Zhaoxin Feng, Emmanuele Chersoni +1Large Language Model CompressionModel and Context Compression

  30. DynaCalKV: Key-Value Cache Compression via Head Grouping and Adaptive Rank Allocation

    Jul 27, 2026Tan T. Nguyen, Quan V. DangKey-Value Cache CompressionLarge Language Model Compression

  31. LLM-based Source Code Compression via Thresholded Symbol Ranking

    Jul 27, 2026Angelo Nardone, Paolo FerraginaLarge Language Model CompressionModel and Context Compression

  32. CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning

    Jul 20, 2026Zhiren Gong, Zihao Zeng, Zijie Wang +3Structured PruningLarge Language Model Compression

  33. SALT: Salience-Aware Lexical Trie for Long-Context Compression

    Jul 20, 2026Oteo Mamo, Hyunjin Yi, Joydhriti Choudhury +2Efficient Long-Context InferenceLarge Language Model Memory

  34. ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation

    Jul 14, 2026Qingyu Zhang, Qianhao Yuan, Hongyu Lin +7On-Policy DistillationLarge Language Model Compression

  35. A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs

    Jul 14, 2026Rahul Krishnan, Volker SchulzKey-Value Cache CompressionKey-Value Cache

  36. Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data

    Jul 13, 2026Shikai Qiu, Marc Finzi, Yujia Zheng +2Large Language Model CompressionModel and Context Compression

  37. CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA

    Jul 11, 2026Gengyu Zhang, Haiyin Ran, Zhengbao He +4Standard Low-Rank AdaptationLarge Language Model Compression

  38. BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression

    Jul 9, 2026Yuantian Shao, Peisong Wang, Zhilei Liu +6Large Language Model Compression

  39. Prompt Compression via Activation Aggregation

    Jul 9, 2026Thibaud Ardoin, Semira Einsele, Evis Bregu +1Large Language Model CompressionModel Activations

  40. LUMI: Tokenizer-Agnostic LLM-Based Lossless Image Compression

    Jul 9, 2026Chris Xing Tian, Chengkai Wu, Ziyu Wang +6Image CompressionLarge Language Model Compression

  41. What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents

    Jul 9, 2026Ashwin Gerard Colaco, Nada LahjoujiCompactionAgent Memory

  42. PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning

    Jul 8, 2026Yazdan Jamshidi, Alexey ShvetsMagnitude-Based PruningStructured Pruning

  43. CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents

    Jul 6, 2026Yujiang Li, Zhenyu Hou, Yi Jing +2CompactionAgentic Reinforcement Learning

  44. LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression

    Jul 3, 2026Zhuowen Liu, Longkun Hao, Shiyu Feng +3Large Language Model CompressionSingular Value Decomposition

  45. MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression

    Jul 1, 2026Sheng Qiang, Ruiwei Chen, Yinpeng Wu +5Key-Value Cache CompressionEfficient Long-Context Inference

  46. FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language Models

    Jun 26, 2026Fan Mo, Yuxuan Han, Geng Zhang +2Large Language Model CompressionMagnitude-Based Pruning

  47. Output-Space Allocation Costs for Calibration-Guided LLM Compression: An Empirical Study

    Jun 26, 2026Qiong Tang, Xiangkun Hu, Xiangyang Liu +2Large Language Model CompressionKnapsack Constraint

  48. SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference

    Jun 25, 2026Haoqian Meng, Yilun Luo, Yafei Zhao +4Large Language Model QuantizationLarge Language Model Compression

  49. EPTS: Elastic Post-Training Sparsity for Efficient Large Language Model Compression

    Jun 24, 2026Ke Xu, Jiaqi Wan, Wenhao Hu +2Large Language Model CompressionSparsity

  50. Scaling Laws for Task-Specific LLM Distillation

    Jun 23, 2026Lavinia Ghita, Dhruv Desai, Ioana BoierLarge Language Model CompressionDataset Distillation

  51. SVD-Surgeon: Optimal Singular-Value Surgery for Large Language Model Compression

    Jun 22, 2026Mahmoud Safari, Frank HutterLarge Language Model CompressionSingular Value Decomposition

  52. UniRank: Unified Rank Allocation for Low-Rank LLM Compression

    Jun 20, 2026Chao Han, Yongjie Du, Junjie Tan +1Large Language Model CompressionLow-Rank Factorization

  53. Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs

    Jun 18, 2026Nico Harder, Daniel Becking, Karsten Mueller +1Large Language Model CompressionLow-Rank Factorization

  54. AnchorKV: Safety-Aware KV Cache Compression via Soft Penalty with a Refusal Anchor

    Jun 16, 2026Ning Ni, Yingjie LaoKey-Value Cache CompressionLarge Language Model Safety

  55. Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training

    Jun 15, 2026Sameera Ramasinghe, Ajanthan Thalaiyasingam, Hadi Mohaghegh Dolatabadi +5Large Language Model CompressionEfficient Long-Context Inference

  56. Beyond Layer Importance in Layer-wise Sparsity: An Inter-Layer Perturbation-Absorption Perspective

    Jun 13, 2026Tao Jing, Ningxin Wu, Chen Kang +3Magnitude-Based PruningSparsity

  57. PolyKV: Heterogeneous Retention and Allocation for KV Cache Compression

    Jun 13, 2026Chao Fei, Panos KalnisKey-Value Cache CompressionKey-Value Cache

  58. Context-Driven Incremental Compression for Multi-Turn Dialogue Generation

    Jun 10, 2026Yeongseo Jung, Jaehyeok Kim, Eunseo Jung +5Dialogue BenchmarksEfficient Long-Context Inference

  59. Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models

    Jun 10, 2026Changyue Wang, Weihang Su, Qingyao Ai +5Large Language Model CompressionLLM Inference Efficiency

  60. Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering

    Jun 10, 2026Haoning Xu, Zhaoqing Li, Huimeng Wang +4Large Language Model CompressionMagnitude-Based Pruning