English
Related papers

Related papers: Activation Compression in LLMs: Theoretical Analys…

200 papers

Large language models (LLMs) have recently emerged as powerful tools for tackling many language-processing tasks. Despite their success, training and fine-tuning these models is still far too computationally and memory intensive. In this…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Roy Miles , Pradyumna Reddy , Ismail Elezi , Jiankang Deng

Deep neural networks have achieved state-of-the-art performance across numerous applications, but their high memory and computational demands present significant challenges, particularly in resource-constrained environments. Model…

Machine Learning · Computer Science 2026-02-18 Shihao Zhang , Rayan Saab

Prompt engineering enables Large Language Models (LLMs) to perform a variety of tasks. However, lengthy prompts significantly increase computational complexity and economic costs. To address this issue, we study six prompt compression…

Computation and Language · Computer Science 2025-05-02 Zheng Zhang , Jinyi Li , Yihuai Lan , Xiang Wang , Hao Wang

Full fine-tuning of Large Language Models (LLMs) is notoriously memory-intensive, primarily because conventional optimizers such as SGD or Adam assume access to exact gradients derived from cached activations. Existing solutions either…

Machine Learning · Computer Science 2025-10-28 Jing Yang , Kaitong Cai , Yijia Fan , Yufeng Yang , Keze Wang

The full-size MLPs and the projection layers in attention introduce tremendous model sizes of large language models (LLMs), consuming extensive computational resources in pre-training. We empirically observe that the activations of…

Machine Learning · Computer Science 2025-10-03 Ziyue Liu , Ruijie Zhang , Zhengyang Wang , Mingsong Yan , Zi Yang , Paul Hovland , Bogdan Nicolae , Franck Cappello , Sui Tang , Zheng Zhang

Approaches for compressing large-language models using low-rank decomposition have made strides, particularly with the introduction of activation and loss-aware SVD, which improves the trade-off between decomposition rank and downstream…

Machine Learning · Computer Science 2025-12-17 Sidhant Sundrani , Francesco Tudisco , Pasquale Minervini

In this paper, we introduce a new post-training compression paradigm for Large Language Models (LLMs) to facilitate their wider adoption. We delve into LLM weight low-rank decomposition, and find that the challenges of this task stem from…

Computation and Language · Computer Science 2025-08-29 Zhihang Yuan , Yuzhang Shang , Yue Song , Dawei Yang , Qiang Wu , Yan Yan , Guangyu Sun

Matrix-level low-rank compression is a promising way to reduce the cost of large language models, but running compression and evaluating the resulting models on language tasks can be prohibitively expensive. Can compression-induced…

Machine Learning · Computer Science 2026-04-21 Mingxue Xu

LLM-powered agents often use prompt compression to reduce inference costs, but this introduces a new security risk. Compression modules, which are optimized for efficiency rather than safety, can be manipulated by adversarial inputs,…

Cryptography and Security · Computer Science 2025-11-18 Zesen Liu , Zhixiang Zhang , Yuchong Xie , Dongdong She

Communication compression is a crucial technique for modern distributed learning systems to alleviate their communication bottlenecks over slower networks. Despite recent intensive studies of gradient compression for data parallel-style…

Machine Learning · Computer Science 2023-03-08 Jue Wang , Binhang Yuan , Luka Rimanic , Yongjun He , Tri Dao , Beidi Chen , Christopher Re , Ce Zhang

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…

Machine Learning · Computer Science 2024-10-07 Rongzhi Zhang , Kuang Wang , Liyuan Liu , Shuohang Wang , Hao Cheng , Chao Zhang , Yelong Shen

In this report, we investigate the potential use of large language models (LLM's) in the task of data compression. Previous works have demonstrated promising results in applying LLM's towards compressing not only text, but also a wide range…

Computation and Language · Computer Science 2026-01-07 Chen-Han Tsai

This work investigates context compression for Large Language Models (LLMs) using learned compression tokens to reduce the memory and computational demands of processing long sequences. We demonstrate that pre-trained LLMs can be fine-tuned…

Computation and Language · Computer Science 2025-11-12 Dmitrii Tarasov , Elizaveta Goncharova , Kuznetsov Andrey

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing benchmarks. However, the escalating scale of model parameters imposes prohibitive memory overheads during training,…

Machine Learning · Computer Science 2026-04-28 Ziqing Wen , Ping Luo , Jiahuan Wang , Kun Yuan , Dongsheng Li , Tao Sun

Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficiency. Instruction-related visual token compression demonstrates strong task relevance, which…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Lei Lei , Jie Gu , Xiaokang Ma , Chu Tang , Jingmin Chen , Tong Xu

Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, some anomalies indicate that even a well-conducted alignment…

Computation and Language · Computer Science 2025-09-24 Jiaming Ji , Kaile Wang , Tianyi Qiu , Boyuan Chen , Jiayi Zhou , Changye Li , Hantao Lou , Juntao Dai , Yunhuai Liu , Yaodong Yang

Asynchronous computation and gradient compression have emerged as two key techniques for achieving scalability in distributed optimization for large-scale machine learning. This paper presents a unified analysis framework for distributed…

Optimization and Control · Mathematics 2018-11-30 Sarit Khirirat , Hamid Reza Feyzmahdavian , Mikael Johansson

Large Language Models (LLMs) demonstrate exceptional performance across various tasks but demand substantial computational resources even for fine-tuning computation. Although Low-Rank Adaptation (LoRA) significantly alleviates memory…

Machine Learning · Computer Science 2025-02-04 Guanduo Chen , Yutong He , Yipeng Hu , Kun Yuan , Binhang Yuan

Safety alignment in Large Language Models (LLMs) remains highly fragile during fine-tuning, where even benign adaptation can degrade pre-trained refusal behaviors and enable harmful responses. Existing defenses typically constrain either…

Artificial Intelligence · Computer Science 2026-04-15 Songping Peng , Zhiheng Zhang , Daojian Zeng , Lincheng Jiang , Xieping Gao

The efficient implementation of large language models (LLMs) is crucial for deployment on resource-constrained devices. Low-rank tensor compression techniques, such as tensor-train (TT) networks, have been widely studied for…

Computation and Language · Computer Science 2025-10-14 Ryan Solgi , Kai Zhen , Rupak Vignesh Swaminathan , Nathan Susanj , Athanasios Mouchtaris , Siegfried Kunzmann , Zheng Zhang