English
Related papers

Related papers: DipSVD: Dual-importance Protected SVD for Efficien…

200 papers

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

The Key-Value (KV) cache is central to the efficiency of transformer-based large language models (LLMs), storing previously computed vectors to accelerate inference. Yet, as sequence length and batch size grow, the cache becomes a major…

Machine Learning · Computer Science 2025-12-08 Damien Lesens , Beheshteh T. Rakhshan , Guillaume Rabusseau

Singular Value Decomposition (SVD) has become an important technique for reducing the computational burden of Vision Language Models (VLMs), which play a central role in tasks such as image captioning and visual question answering. Although…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Haiyu Wang , Yutong Wang , Jack Jiang , Sai Qian Zhang

With the proliferation of task-specific large language models, delta compression has emerged as a method to mitigate the resource challenges of deploying numerous such models by effectively compressing the delta model parameters. Previous…

Computation and Language · Computer Science 2025-04-21 Yan Yang , Yixia Li , Hongru Wang , Xuetao Wei , Jianqiao Yu , Yun Chen , Guanhua Chen

Vision-Language Models (VLMs) are integral to tasks such as image captioning and visual question answering, but their high computational cost, driven by large memory footprints and processing time, limits their scalability and real-time…

Machine Learning · Computer Science 2025-10-21 Yutong Wang , Haiyu Wang , Sai Qian Zhang

Large Language Models (LLMs) present significant deployment challenges due to their immense size and computational requirements. Model compression techniques are essential for making these models practical for resource-constrained…

Key-Value cache (\texttt{KV} \texttt{cache}) compression has emerged as a promising technique to optimize Large Language Model (LLM) serving. It primarily decreases the memory consumption of \texttt{KV} \texttt{cache} to reduce the…

Machine Learning · Computer Science 2025-04-01 Wei Gao , Xinyu Zhou , Peng Sun , Tianwei Zhang , Yonggang Wen

In the field of large language model (LLM) compression, singular value decomposition (SVD) is a widely studied and adopted low-rank decomposition technique. Since SVD operates exclusively on linear modules, and these modules in LLMs are…

Machine Learning · Computer Science 2025-10-23 Lin Xv , Jingsheng Gao , Xian Gao , Ting Liu , Yuzhuo Fu

Storing data is particularly a challenge when dealing with image data which often involves large file sizes due to the high resolution and complexity of images. Efficient image compression algorithms are crucial to better manage data…

Computer Vision and Pattern Recognition · Computer Science 2024-06-10 Zahra Golpayegani , Nizar Bouguila

Orthonormality is the foundation of matrix decomposition. For example, Singular Value Decomposition (SVD) implements the compression by factoring a matrix with orthonormal parts and is pervasively utilized in various fields. Orthonormality,…

Data Structures and Algorithms · Computer Science 2021-12-08 Huiwen Wang , Yanwen Zhang , Jichang Zhao

Low-rank approximation methods such as singular value decomposition (SVD) and its variants (e.g., Fisher-weighted SVD, Activation SVD) have recently emerged as effective tools for neural network compression. In this setting, decomposition…

Machine Learning · Computer Science 2025-12-02 Haoran Qin , Shansita Sharma , Ali Abbasi , Chayne Thrash , Soheil Kolouri

Singular Value Decomposition (SVD) has recently seen a surge of interest as a simple yet powerful tool for large language models (LLMs) compression, with a growing number of works demonstrating 20-80% parameter reductions at minimal…

Machine Learning · Computer Science 2025-08-05 Zishan Shao , Yixiao Wang , Qinsi Wang , Ting Jiang , Zhixu Du , Hancheng Ye , Danyang Zhuo , Yiran Chen , Hai Li

For the efficient inference of Large Language Models (LLMs), the effective compression of key-value (KV) cache is essential. Three main types of KV cache compression techniques, namely sparsity, channel compression, and quantization, have…

Machine Learning · Computer Science 2025-02-24 Hong Yankun , Li Xing , Zhen Hui-Ling , Yu Xianzhi , Liu Wulong , Yuan Mingxuan

Supervised Fine-Tuning (SFT) empowers Large Language Models (LLMs) with exceptional performance on specialized tasks, but it yields dense, high-dimensional delta parameters that pose severe storage and distribution challenges. Singular…

Machine Learning · Computer Science 2026-02-17 Boya Xiong , Shuo Wang , Weifeng Ge , Guanhua Chen , Yun Chen

The massive scale of pretrained models has made efficient compression essential for practical deployment. Low-rank decomposition based on the singular value decomposition (SVD) provides a principled approach for model reduction, but its…

Machine Learning · Computer Science 2026-04-06 Farhad Pourkamali-Anaraki

As Large Language Models (LLMs) continue to scale in parameter count, deploying them on commodity hardware has become increasingly challenging. Post-Training Quantization (PTQ) addresses this by reducing the precision of model weights,…

Machine Learning · Computer Science 2025-12-03 Shashank Landge , Abhishek Patil , Tejas kamble , Bhushan Buddhivant , Priyanka Joshi

Low-rank decomposition has emerged as an important problem in Large Language Model (LLM) fine-tuning and inference. Through Singular Value Decomposition (SVD), the weight matrix can be factorized into low-rank spaces optimally. Previously,…

Machine Learning · Computer Science 2026-04-02 Yuhang Li , Donghyun Lee , Ruokai Yin , Priyadarshini Panda

Personalized text-to-image models such as DreamBooth require fine-tuning large-scale diffusion backbones, resulting in significant storage overhead when maintaining many subject-specific models. We present Delta-SVD, a post-hoc,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Tangyuan Zhang , Shangyu Chen , Qixiang Chen , Jianfei Cai

Engineering simulations are usually based on complex, grid-based, or mesh-free methods for solving partial differential equations. The results of these methods cover large fields of physical quantities at very many discrete spatial…

Fluid Dynamics · Physics 2025-08-08 Eduardo Di Costanzo , Niklas Kühl , Jean-Christophe Marongiu , Thomas Rung

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