A Survey on Model Compression for Large Language Models

Zhu, Xunyu, Li, Jian, Liu, Yong, Ma, Can, Wang, Weiping·2024·Transactions of the Association for Computational Linguistics
DOI 10.1162/tacl_a_00704

Cited by (365)

Items 301–365 of 365

  1. Developing a Lightweight On-Device LLM Agent for Real-Time Privacy Monitoring in Resource-Conscious POS Systems
    Consilia Mukum, Yanzhen Qu · 2026 · European Journal of Electrical Engineering and Computer Science
  2. Act Before It’s Too Late: Power-Efficient LLM Inference on Mobile Device
    Haolin Chu, Jinxiao Fan, Jiabin Deng, Bensong Yu, Liguang Xie, Liang Liu, Huadóng Ma, Xiaolong Zheng · 2026 · International Conference on Mobile Systems, Applications, and Services
  3. A Deep Learning-Based Computer Vision Framework for Intelligent Image Recognition
    Yichen Wu · 2026 · International Conference on Big Data and Informatization Education (ICBDIE)
  4. Layer-Adaptive Self-Distilled Quantization for Efficient Large Language Model Compression
    Kosar Abdi, Ahmad Mohammadi · 2026 · SSRN Electronic Journal
  5. Practical Implementation and Assessment of Post-Training Quantization Methods for Large Language Models
    Avinash. H M, Aditi Singarajipura, Pethuru Raj · 2026 · International Conference on Integrated Intelligence and Communication Systems (ICIICS)
  6. A Survey on Memory-Efficient Fine-Tuning for Large Language Models
    Yeachan Kim, Mingyu Lee, SangKeun Lee · 2026 · Transactions of the Association for Computational Linguistics
  7. FT-Sparse: Algorithm-Based Fault Tolerance for Sparse CNNs Using Structured Sparsity in GPUs
    Josie E. Rodriguez Condia, Mohammad Hasan Ahmadilivani, Jaan Raik, Maksim Jenihhin, Matteo Sonza Reorda · 2026 · IEEE VLSI Test Symposium (VTS)
  8. The landscape of pruning for large language models: A systematic review and unified taxonomy
    Yiyi Chen, Yuchuan Mu, Qiang Tong, X C Liu · 2026 · Neural Networks
  9. Energy-Aware Edge–Cloud Collaboration for Learning Varieties of English: Cache-Assisted Inference and Evidence-Grounded Feedback
    Cunqian You, 张世伟, Lu Qi, Miao Wei, X Y Wang, Huijuan Lu · 2026 · AI Engineering
  10. Survey on joint compression and fine-tuning of large language models: Methods, toolchains, and open challenges under resource constraints
    Jihyeon Kim, Hanyong Lee, Jaesung Lee · 2026 · Neurocomputing
  11. Heterogeneous Collaborative Inference Architecture for Large Language Models
    D Xu · 2026 · International Conference on Sensor-Cloud and Edge Computing System (SCECS)
  12. FORCE: Federated Orthogonality-Aware Low-Rank Adaptation for Communication-Efficient Fine-Tuning
    La Van Quan, Junming Huang, Huy N. Le, Phuong Tran, Tung-Anh Nguyen, Phuong Luu Vo, Bing Bing Zhou, Nguyen Hoang Khoi Tran · 2026 · IEEE Networking Letters
  13. xCCLTuner: Treating xCCL as Black-Box and Automatically Tuning
    Ce Wang, Wentao Fan, Zhehao Lin, Peirui Cao, Xi Lin, Xiaohu Xu, Wanchun Dou, Guihai Chen, Chen Tian · 2026 · IEEE Conference on Computer Communications (INFOCOM)
  14. EQUIP: EQUivariant preserving In-Place updates for Efficient Token Pruning
    Arun Ramachandran, R. Govindarajan, Murali Annavaram, Prakash Raghavendra · 2026 · Proceedings of the conference - Association for Computational Linguistics. Meeting
  15. Optimizing Open Large Language Models for Equity and Accessibility in Higher Education Through Pruning and Retrieval-Augmented Generation
    Iván Miguel García-López, José Martín Molina Espinosa, María Soledad · 2026 · IEEE Revista Iberoamericana de Tecnologias del Aprendizaje
  16. Challenges and strategies for harnessing large language models in plant protection
    X Y Li, Wenjie Shangguan, Lidong Cao, Huizhu Yuan, Xiaojing Yan · 2026 · Frontiers in Plant Science
  17. Generative AI at the Edge: A Comprehensive Survey of Architectures, Hardware and Applications
    Mozhgan Navardi, Yuzhe Fu, Yueqian Lin, Hai Helen Li, Yiran Chen, Tinoosh Mohsenin · 2026 · ACM Computing Surveys
  18. NOVA: Noise-to-variation guided pruning of large language models
    Anran Ding, Peng Xu, Zhihong Jin · 2026 · Knowledge-Based Systems
  19. Evaluating large language model compression: a comparative analysis on state-of-the-art models across diverse hardware platforms
    Dominik Hildebrand, Benjamin Kiefer, Andreas Zell · 2026 · Artificial Intelligence Review
  20. Panther: Faster and Cheaper Computations with Randomized Numerical Linear Algebra
    Fahd Seddik, Abdulrahman Elbedewy, Gaser Elmasry, Mohamed Abdelmoniem, Yahia Zakaria · 2026 · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE)
  21. Capability-Specific Degradation Patterns in Quantized Small Language Models
    Emil Rahimov · 2026 · International Journal of Artificial Intelligence
  22. LAGR: Compensate Layer Pruning with Adaptive Gated Residuals for Efficient Compression
    Yuchuan Mu, Yuehua Chen, Bo Hao Cheng, Peng Li, Jianping Hu · 2026 · Lecture notes in computer science
  23. Distilling large language models for code generation via ranking supervision
    Zhe Ding, Hui Ji, Su Pan, Miao Chi · 2026 · Neural Networks
  24. Green AI Beyond Operational Energy GAILA: A Lifecycle-Oriented Environmental Reporting and Decision-Support Framework for Large Language Models Conceptual Article / Working Paper
    Alyaa Sabri Awadh · 2026 · SSRN Electronic Journal
  25. Chain-of-thought Responses to Misleading Context under Quantization in Small Language Models
    Danish Naseer, Ebaad Raheem · 2026 · SSRN Electronic Journal
  26. Komparasi Support Vector Machine dengan Logistic Regression terhadap klasifikasi pada data asma
    Tiara Utary Grace Moelyono, Adi Setiawan, Rachel Wulan Nirmalasari Wijaya · 2026 · Jurnal Sains dan Edukasi Sains
  27. FedDAFL-Lite: A Federated Lightweight Machine Learning Model for Embedded AI in the Global South
    Antoine Bagula, Nathan Mbayo, Ferdinand Kahenga · 2026 · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
  28. Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges
    Chenqi Li, Minghui Min, Dusit Niyato, Wei Ni · 2026 · Research Square
  29. Communication-Efficient Training of Large Language Models with 1-Bit Allreduce for ZeRO
    Wenqi Liu, Yihao Xie, Chunbao Zhou, Boyao Zhang, Ningming Nie · 2026 · IEEE International Conference on Big Data Security on Cloud, IEEE International Conference on High Performance and Smart Computing, and IEEE International Conference on Intelligent Data and Security (BigDataSecurity/HPSC/IDS)
  30. Efficient Adaptation of Large Language Models for Sentiment Classification: A Comparative Study of QLoRA, LoRA, and Full Fine-Tuning Under Resource Constraints
    Tejaswini Ghosh, Sini Anna Alex · 2026 · International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE)
  31. Adaptive Local LLM Compression Under Dynamic Edge Constraints
    Pardeep Singh, Azhar Ashraf, Saksham Sharma, Dhruv Soni, Jolly Tomar · 2026 · International Conference on Power, Control and Computing Technologies (ICPC2T)
  32. MetaPAC: Adaptive Compression Across Transformer Architectures
    Tamás Panyi, Attila Farkas, Gábor Kertész · 2026 · IEEE International Conference on Intelligent Engineering Systems (INES)
  33. From carbon-intensive to carbon-neutral: sustainability and energy efficiency in small language models: bibliometric analysis (2020–2026)
    Avinash Shrivastava, Anamika Gupta, Sarabjeet Kaur Kochhar · 2026 · Applied Computing and Intelligence
  34. Q-SA2: Enhanced low-bit quantization-aware fine-tuning via structure-aware adaptation
    Yuning Yang, Guowei Peng, Xiurui Xie, Dongyang Zhang, Guangchun Luo, Guisong Liu · 2026 · Neural Networks
  35. LLM-driven paradigm for agent-based modeling and simulation: A review and organizing framework
    Jiaqi Wang, Xiong Li, Gang Xiao · 2026 · Computer Science Review
  36. BlockLLM-E2MR: Blockchain-attested LLM-guided energy-efficient multipath routing for mobile ad hoc networks
    Haridas S · 2026 · International Journal of Applied Resilience and Sustainability
  37. Green Conversational AI at the Edge: Energy-Aware Optimization and Adaptive Quantization for Sustainable LLM Inference
    SATYA KARTEEK GUDIPATI, NAVEEN ANAND MISHRA, GOPIKANTH ANKAM · 2026 · Lecture notes in networks and systems
  38. Finding the Efficiency Sweet Spot in Compressed Large Language Models Through Resource and Cost Analysis
    Okan Karaoglan, Georg Rottenwalter, Gerd Beneken · 2026 · Lecture notes in networks and systems
  39. Медианные значения критериев качества генерации обзоров при сравнении с альтернативными подходами
    Илия Кузнецов · 2026 · Cifra LLC Journals
  40. Методика предварительной оценки и отбора цитатных фрагментов для повышения эффективности генерации научных обзорных текстов
    Илия Кузнецов · 2026 · CyberLeninK (CyberLeninka)
  41. Основные этапы работы программного комплекса для цитатно-осведомленного формирования обзорных текстов
    Илия Кузнецов · 2026 · Cifra LLC Journals
  42. Основные параметры конфигурации системы при проведении эксперимента
    Илия Кузнецов · 2026 · Cifra LLC Journals
  43. Медианные значения критериев качества генерации обзоров для рассматриваемых моделей и подходов
    Илия Кузнецов · 2026 · Cifra LLC Journals
  44. Human-in-the-loop formative assessment with smaller language models: An equivalence testing study in programming education
    Pedro C. Mendonça, Filipe Quintal, Mário A. T. Figueiredo, Fábio Mendonça · 2026 · Computers in Human Behavior Reports
  45. Learning to Compress: Energy-Aware Large Language Model Serving via Adaptive KV Caching
    Yuanbin Cheng, Zhentong Shao, Nanpeng Yu, Yu Fu, Yue Dong · 2026 · IEEE Power Engineering Society General Meeting
  46. MKE: A Lightweight Framework for Multimodal Knowledge Extraction via Knowledge Distillation
    Sijie Liu, Xuming Ye, Xingyu Wang, Lianshuai Wang, Weiyu Dong, Meng An · 2026 · Electronics
  47. Shortcut-Aware Logic-Sinking Distillation with Budget-Adaptive Decision Control for Efficient Long-Horizon Reasoning
    Jiangbo Feng, Jinchao Guo, Yuxiang He, Qi Zeng, Ke Wang, Shifeng Lin, Jiayang Lai · 2026 · International Journal of Pattern Recognition and Artificial Intelligence
  48. Towards Emotion-Aware Wearables: Distilling PPG Foundation Models for Real-Time Affective and Physiological Monitoring
    Quang Duc Nguyen, Patrick Le Callet, Thanh Ha Le, Thi Duyen Ngo · 2026 · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR)
  49. FROM CLOUD TO EDGE: A COMPREHENSIVE REVIEW OF OPTIMIZATION STRATEGIES FOR ON-DEVICE LARGE LANGUAGE MODELS
    Mohammad Mohammad, Qutaiba Ibrahim Ali · 2026 · ITEGAM- Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA)
  50. Rank and data adaptive low-rank adaptation for 2-bit quantization-aware fine-tuning of ViT
    Yuning Yang, Guowei Peng, Xiurui Xie, Dongyang Zhang, Guisong Liu · 2026 · Pattern Recognition
  51. INTERLACE: Interleaved Layer Pruning and Efficient Adaptation in Large Vision-Language Models
    Parsa Madinei, Ryan Solgi, Ziqi Wen, Jonathan Skaza, Miguel P. Eckstein, Ramtin Pedarsani · 2026
  52. Structured Pruning of Small Language Models: An Empirical Study on GQA-Aware Attention and MLP Compression with LoRA Recovery
    ADNANE BAKKOU, Badr Hirchoua, Mouad Banane, Naoufal Er-raji · 2026 · International Journal of Advances in Soft Computing and its Applications
  53. Efficient zero-shot post-training quantization of large language models
    Sami Ul Haq, Aiman Helmi El-Maleh, Ali Alsuwaiyan · 2026 · Neural Networks
  54. Cost-Efficient Strategies for Production Indonesian Sentiment Analysis: Open-Source Models, Commercial LLMs, and Hybrid Pipelines
    Ridwan Ilyas, Mochammad Arif Bijaksana · 2026 · Jurnal Teknik Informatika (Jutif)
  55. Large Language Model Compression for Autoregressive Text Generation: Methods, Evaluation, and Deployment Trade-Offs
    Chenhui Zhu, Runhua Zhang, Fangzheng Tian · 2026 · Electronics
  56. Perplexity-Spectrum Calibration for Post-Training Pruning of Large Language Models
    Qizhu Wang, Xingzhou Zhang, Zhihao Qu, Wenfeng Xu, Wentao Wang · 2026 · International Joint Conference on Neural Networks (IJCNN)
  57. Multimodal Large-Model-Driven Method for Urban 3D Green-Space Calculation and Low-Carbon Green-Space Management
    Yi Yang · 2026 · Computation
  58. EDGE AI FOR SECURE AND FAST RESPONSE: A ZERO-EGRESS ARCHITECTURE FOR QUANTISED SMALL LANGUAGE MODELS WITH SANDBOXED RETRIEVAL AUGMENTATION
    2026 · International Journal of Progressive Research in Engineering Management and Science
  59. FuseDot: A Multiplication-Fused Dot Product Accelerator for Efficient LLM Inference
    Wenju Zhao, Jianhui Yue, Pengcheng Yao, Yujia Cui, Qinggang Wang, Yufei Sun, Jiaqi Zhai, Hai Jin, Xiaofei Liao · 2026 · ACM/IEEE Design Automation Conference (DAC)
  60. Ekstraksi Data Formulir Downtime Tulisan Tangan Menggunakan Vision-Language Model Qwen2.5-VL Lokal pada Sistem Pencatatan Produksi PT Intiroda Makmur
    Budy Satria, Muhammad Dawi Syauqi · 2026 · Saturnus
  61. Lightweight Pruning Algorithm for Multimodal Large Models Oriented to Educational APPs
    Xinghan Li, Xiaoling Bai, Wenrui Xue, Dewang Ye · 2026 · International Conference on Intelligent Education and Computer Technology (IECT)
  62. Structured Pruning and Lightweight Adaptation of Foundation Models for Resource-Efficient Earth Observation
    Aniket Ramchandra Munde, Kartheek Kumar Reddy Nareddy, Julia Niebling · 2026
  63. Importance-Guided Structural Pruning of Aya Expanse 8B and Gemma-3-12B for English–Chinese Machine Translation
    Havish Balaga, Anish Racherla, Kolupoti Kiran, Saumitra Yadav, Manish Shrivastava · 2026 · Conference on Machine Translation (WMT)
  64. GridDistill: A Systematic Approach to Bridging the Capacity Gap in Clinical Image Classification
    José Manuel Meza González, Jesús García-Ramírez, Valentín Trujillo Mora · 2026 · Lecture notes in networks and systems
  65. Mapping the Patent Frontier of On-Device LLMs in Mobile Software Engineering
    Mohamad Kassab · 2026 · IEEE/ACM International Conference on Mobile Software Engineering and Systems (MOBILESoft)