English
Related papers

Related papers: IO-SVD: Input-Output Whitened SVD for Adaptive-Ran…

200 papers

Large Language Models (LLMs) have enabled remarkable progress in natural language processing, yet their high computational and memory demands pose challenges for deployment in resource-constrained environments. Although recent low-rank…

Computation and Language · Computer Science 2026-02-09 Jiayi Tian , Ryan Solgi , Jinming Lu , Yifan Yang , Hai Li , Zheng Zhang

Despite extensive efforts to align Large Language Models (LLMs) with human values and safety rules, jailbreak attacks that exploit certain vulnerabilities continuously emerge, highlighting the need to strengthen existing LLMs with…

Machine Learning · Computer Science 2025-09-30 Xuekang Wang , Shengyu Zhu , Xueqi Cheng

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

Parameter-efficient fine-tuning (PEFT) is a scalable approach for adapting large speech foundation models to new domains. While methods such as LoRA and its state-of-the-art variants reduce adaptation costs, they typically allocate…

Sound · Computer Science 2026-01-21 Pu Wang , Shinji Watanabe , Hugo Van hamme

Post-training fundamentally alters the behavior of large language models (LLMs), yet its impact on the internal parameter space remains poorly understood. In this work, we conduct a systematic singular value decomposition (SVD) analysis of…

Machine Learning · Computer Science 2026-01-30 Xinyu He , Xianghui Cao

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

Large language models (LLMs) have demonstrated remarkable capabilities, yet prohibitive parameter complexity often hinders their deployment. Existing singular value decomposition (SVD) based compression methods simply deem singular values…

Computation and Language · Computer Science 2025-02-24 Dengjie Li , Tiancheng Shen , Yao Zhou , Baisong Yang , Zhongying Liu , Masheng Yang , Bernard Ghanem , Yibo Yang , Yujie Zhong , Ming-Hsuan Yang

Self-supervised learning (SSL) has emerged as a crucial technique in image processing, encoding, and understanding, especially for developing today's vision foundation models that utilize large-scale datasets without annotations to enhance…

Computer Vision and Pattern Recognition · Computer Science 2025-01-08 Chuang Niu , Wenjun Xia , Hongming Shan , Ge Wang

The Fisher information is a fundamental concept for characterizing the sensitivity of parameters in neural networks. However, leveraging the full observed Fisher information is too expensive for large models, so most methods rely on simple…

Machine Learning · Computer Science 2025-05-26 Viktoriia Chekalina , Daniil Moskovskiy , Daria Cherniuk , Maxim Kurkin , Andrey Kuznetsov , Evgeny Frolov

Large language models (LLMs) have demonstrated remarkable performance, but their long-context reasoning remains constrained by the excessive memory required for the Key-Value (KV) cache. This makes KV cache compression a critical step…

Machine Learning · Computer Science 2025-09-30 Xianglong Yan , Zhiteng Li , Tianao Zhang , Haotong Qin , Linghe Kong , Yulun Zhang , Xiaokang Yang

Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value (KV) cache during…

Computation and Language · Computer Science 2025-07-16 Luohe Shi , Zuchao Li , Lefei Zhang , Guoming Liu , Baoyuan Qi , Hai Zhao

We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs). RSD synergistically combines a lightweight draft model with a more powerful target…

Computation and Language · Computer Science 2025-06-27 Baohao Liao , Yuhui Xu , Hanze Dong , Junnan Li , Christof Monz , Silvio Savarese , Doyen Sahoo , Caiming Xiong

Modern deep neural networks (DNNs) often require high memory consumption and large computational loads. In order to deploy DNN algorithms efficiently on edge or mobile devices, a series of DNN compression algorithms have been explored,…

Machine Learning · Computer Science 2020-04-21 Huanrui Yang , Minxue Tang , Wei Wen , Feng Yan , Daniel Hu , Ang Li , Hai Li , Yiran Chen

Large Language Models (LLMs) are very demanding in terms of their computational resources. Low-rank decompositions of LLM weights, e.g. via Singular Value Decomposition (SVD), is a promising approach for LLM compression, but presents…

Machine Learning · Computer Science 2025-12-04 Roman Rausch , David Jansen , Sukhbinder Singh , Román Orús

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

We address the critical gap between the computational demands of vision-language models and the possible ultra-low-bit weight precision (bitwidth $\leq2$ bits) we can use for higher efficiency. Our work is motivated by the substantial…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Xijun Wang , Junyun Huang , Rayyan Abdalla , Chengyuan Zhang , Ruiqi Xian , Dinesh Manocha

In the realm of Sign Language Translation (SLT), reliance on costly gloss-annotated datasets has posed a significant barrier. Recent advancements in gloss-free SLT methods have shown promise, yet they often largely lag behind gloss-based…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Han Liang , Chengyu Huang , Yuecheng Xu , Cheng Tang , Weicai Ye , Juze Zhang , Xin Chen , Jingyi Yu , Lan Xu

On-device recommendation is critical for a number of real-world applications, especially in scenarios that have agreements on execution latency, user privacy, and robust functionality when internet connectivity is unstable or even…

Information Retrieval · Computer Science 2026-01-15 Xin Xia , Hongzhi Yin , Shane Culpepper

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

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