English
Related papers

Related papers: AA-SVD : Anchored and Adaptive SVD for Large Langu…

200 papers

Vision-Language-Action (VLA) models have made substantial progress by leveraging the robust capabilities of Visual Language Models (VLMs). However, VLMs' significant parameter size and autoregressive (AR) decoding nature impose considerable…

Machine Learning · Computer Science 2025-09-23 Songsheng Wang , Rucheng Yu , Zhihang Yuan , Chao Yu , Feng Gao , Yu Wang , Derek F. Wong

Adaptive gradient-based optimizers such as Adagrad and Adam are crucial for achieving state-of-the-art performance in machine translation and language modeling. However, these methods maintain second-order statistics for each parameter,…

Machine Learning · Computer Science 2019-09-13 Rohan Anil , Vineet Gupta , Tomer Koren , Yoram Singer

In the era of big data, effectively compressing large datasets while performing complex mathematical operations is crucial. Tensor-based decomposition methods have shown superior compression capabilities with minimal loss of accuracy…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-18 Md Taufique Hussain , Grey Ballard , Aditya Devarakonda , Srinivas Eswar , Naman Pesricha , Vishwas Rao

In this paper we propose novel methods for compression and recovery of multilinear data under limited sampling. We exploit the recently proposed tensor- Singular Value Decomposition (t-SVD)[1], which is a group theoretic framework for…

Information Theory · Computer Science 2013-11-01 Zemin Zhang , Gregory Ely , Shuchin Aeron , Ning Hao , Misha Kilmer

Despite recent efforts in understanding the compression impact on large language models (LLMs) in terms of their downstream task performance and trustworthiness on relatively simpler uni-modal benchmarks (for example, question answering,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-10 Souvik Kundu , Anahita Bhiwandiwalla , Sungduk Yu , Phillip Howard , Tiep Le , Sharath Nittur Sridhar , David Cobbley , Hao Kang , Vasudev Lal

Large language models (LLMs) hold great promise for specialized scientific domains such as materials science, yet adapting them efficiently and accurately to domain-specific knowledge remains challenging due to limited data and high…

Computation and Language · Computer Science 2025-03-31 Chuan-Wei Kuo , Siyu Chen , Chenqi Yan , Yu Yang Fredrik Liu

While speech foundation models (SFMs) have demonstrated remarkable performance in audio-only tasks, their adaptation to multimodal scenarios remains underexplored. This work presents UASR-LLM, a novel framework that adapts frozen SFMs to…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-03 Jing-Xuan Zhang , Genshun Wan , Jin Li , Jianqing Gao , Duo Zhao , Zhen-Hua Ling

Serving transformer language models with high throughput requires caching Key-Values (KVs) to avoid redundant computation during autoregressive generation. The memory footprint of KV caching is significant and heavily impacts serving costs.…

Machine Learning · Computer Science 2026-04-28 Anastasiia Filippova , David Grangier , Marco Cuturi , João Monteiro

While Large Language Models (LLMs) have shown remarkable abilities, they are hindered by significant resource consumption and considerable latency due to autoregressive processing. In this study, we introduce Adaptive N-gram Parallel…

Computation and Language · Computer Science 2024-07-11 Jie Ou , Yueming Chen , Wenhong Tian

Stochastic gradient-based descent (SGD), have long been central to training large language models (LLMs). However, their effectiveness is increasingly being questioned, particularly in large-scale applications where empirical evidence…

Machine Learning · Computer Science 2025-07-03 Di Zhang , Yihang Zhang

Learning continuous representations of discrete objects such as text, users, movies, and URLs lies at the heart of many applications including language and user modeling. When using discrete objects as input to neural networks, we often…

Machine Learning · Computer Science 2021-03-12 Paul Pu Liang , Manzil Zaheer , Yuan Wang , Amr Ahmed

Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large models, including large language models for natural language processing and diffusion models for computer vision. This paper proposes a generalized…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Xiangyu Chen , Jing Liu , Ye Wang , Pu Perry Wang , Matthew Brand , Guanghui Wang , Toshiaki Koike-Akino

Lossy image compression is essential for efficient transmission and storage. Traditional compression methods mainly rely on discrete cosine transform (DCT) or singular value decomposition (SVD), both of which represent image data in…

Image and Video Processing · Electrical Eng. & Systems 2025-03-28 Pooya Ashtari , Pourya Behmandpoor , Fateme Nateghi Haredasht , Jonathan H. Chen , Panagiotis Patrinos , Sabine Van Huffel

We extend the randomized singular value decomposition (SVD) algorithm \citep{Halko2011finding} to estimate the SVD of a shifted data matrix without explicitly constructing the matrix in the memory. With no loss in the accuracy of the…

Machine Learning · Statistics 2019-12-02 Ali Basirat

We propose a novel neural waveform compression method to catalyze emerging speech semantic communications. By introducing nonlinear transform and variational modeling, we effectively capture the dependencies within speech frames and…

Sound · Computer Science 2022-12-14 Shengshi Yao , Zixuan Xiao , Sixian Wang , Jincheng Dai , Kai Niu , Ping Zhang

With the rapid development of natural language processing technology, large-scale language models (LLM) have achieved remarkable results in a variety of tasks. However, how to effectively train these huge models and improve their…

Artificial Intelligence · Computer Science 2024-12-09 Jiajing Chen , Bingying Liu , Xiaoxuan Liao , Jia Gao , Hongye Zheng , Yue Li

While overparameterization in machine learning models offers great benefits in terms of optimization and generalization, it also leads to increased computational requirements as model sizes grow. In this work, we show that by leveraging the…

Machine Learning · Computer Science 2026-02-16 Can Yaras , Peng Wang , Laura Balzano , Qing Qu

Low-rank optimization has emerged as a promising direction in training large language models (LLMs) to improve running time and reduce the memory usage of adaptive optimizers by constraining learning to a lower-dimensional space. Prior work…

Machine Learning · Computer Science 2025-10-09 Ionut-Vlad Modoranu , Mher Safaryan , Erik Schultheis , Max Ryabinin , Artem Chumachenko , Dan Alistarh

For data-constrained, complex and dynamic industrial environments, there is a critical need for transferable and multimodal methodologies to enhance anomaly detection and therefore, prevent costs associated with system failures. Typically,…

Adapting billion-parameter language models to a downstream task is still costly, even with parameter-efficient fine-tuning (PEFT). We re-cast task adaptation as output-distribution alignment: the objective is to steer the output…

Computation and Language · Computer Science 2026-03-03 Senkang Hu , Xudong Han , Jinqi Jiang , Yihang Tao , Zihan Fang , Yong Dai , Sam Tak Wu Kwong , Yuguang Fang