English
Related papers

Related papers: Why Smaller Is Slower? Dimensional Misalignment in…

200 papers

Recent advancements in 3D Gaussian Splatting (3DGS) have made a significant impact on rendering and reconstruction techniques. Current research predominantly focuses on improving rendering performance and reconstruction quality using…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Yinlong Bai , Hongxin Zhang , Sheng Zhong , Junkai Niu , Hai Li , Yijia He , Yi Zhou

Low-rank and sparse composite approximation is a natural idea to compress Large Language Models (LLMs). However, such an idea faces two primary challenges that adversely affect the performance of existing methods. The first challenge…

Machine Learning · Computer Science 2026-02-27 Changhai Zhou , Qian Qiao , Yuhua Zhou , Yuxin Wu , Shichao Weng , Weizhong Zhang , Cheng Jin

The rapid scaling of Large Language Models (LLMs) has pushed training workloads far beyond the limits of single-node analysis, demanding a deeper understanding of how these models behave across large-scale, multi-GPU systems. In this paper,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-22 Seokjin Go , Joongun Park , Spandan More , Hanjiang Wu , Irene Wang , Aaron Jezghani , Tushar Krishna , Divya Mahajan

This paper investigates and validates the impact of fine-tuning on large language model performance, focusing on parameter-efficient methods (LoRA and QLoRA). We evaluate model capabilities across three key domains: (1) commonsense…

Computation and Language · Computer Science 2025-06-13 Qingda , Mai

Low Rank Decomposition of matrix - splitting a large matrix into a product of two smaller matrix offers a means for compression that reduces the parameters of a model without sparsification, and hence delivering more speedup on modern…

Computation and Language · Computer Science 2023-09-26 Ayush Kaushal , Tejas Vaidhya , Irina Rish

Vector Symbolic Architecture (VSA) is emerging in machine learning due to its efficiency, but they are hindered by issues of hyperdimensionality and accuracy. As a promising mitigation, the Low-Dimensional Computing (LDC) method…

Machine Learning · Computer Science 2025-03-18 Shijin Duan , Yejia Liu , Gaowen Liu , Ramana Rao Kompella , Shaolei Ren , Xiaolin Xu

Compressed vision-language models (VLMs) are widely used to reduce memory and compute costs, making them a suitable choice for real-world deployment. However, compressing these models raises concerns about whether internal computations and…

Artificial Intelligence · Computer Science 2026-03-27 Veeraraju Elluru , Arth Singh , Roberto Aguero , Ajay Agarwal , Debojyoti Das , Hreetam Paul

Training Large Language Models(LLMs) is one of the most compute-intensive tasks in high-performance computing. Predicting end-to-end training time for multi-billion parameter models distributed across hundreds of GPUs remains challenging…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Biyao Zhang , Mingkai Zheng , Debargha Ganguly , Xuecen Zhang , Vikash Singh , Vipin Chaudhary , Zhao Zhang

This paper introduces Least Volume (LV)--a simple yet effective regularization method inspired by geometric intuition--that reduces the number of latent dimensions required by an autoencoder without prior knowledge of the dataset's…

Machine Learning · Computer Science 2025-09-26 Qiuyi Chen , Cashen Diniz , Mark Fuge

Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-rank Adaptation…

Machine Learning · Computer Science 2026-01-29 Longteng Zhang , Sen Wu , Shuai Hou , Zhengyu Qing , Zhuo Zheng , Danning Ke , Qihong Lin , Qiang Wang , Shaohuai Shi , Xiaowen Chu

High-dimensional biological data often exhibit a severe mismatch between feature dimensionality and sample size, making reliable classification difficult in extremely small-data regimes. In these settings, kernel methods can lose…

Machine Learning · Computer Science 2026-05-21 Alakananda Mitra , David H. Fleisher , Vangimalla Reddy , Chittaranjan Ray

Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Context compression techniques can reduce these costs, but the most effective approaches…

Computation and Language · Computer Science 2025-10-24 Hippolyte Pilchen , Edouard Grave , Patrick Pérez

Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting,…

Computation and Language · Computer Science 2020-06-24 Zhuohan Li , Eric Wallace , Sheng Shen , Kevin Lin , Kurt Keutzer , Dan Klein , Joseph E. Gonzalez

Large language models (LLMs) have achieved remarkable success in many natural language processing (NLP) tasks. To achieve more accurate output, the prompts used to drive LLMs have become increasingly longer, which incurs higher…

Computation and Language · Computer Science 2025-09-19 Yaxin Gao , Yao Lu , Zongfei Zhang , Jiaqi Nie , Shanqing Yu , Qi Xuan

Deep model compression has been extensively studied, and state-of-the-art methods can now achieve high compression ratios with minimal accuracy loss. This paper studies model compression through a different lens: could we compress models…

Machine Learning · Computer Science 2020-01-01 Shupeng Gui , Haotao Wang , Chen Yu , Haichuan Yang , Zhangyang Wang , Ji Liu

Large Language Models (LLMs) have demonstrated exceptional benefits to a wide range of domains, for tasks as diverse as code generation and robot navigation. While LLMs are usually served from cloud data centers, mission-critical and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-13 Mayank Arya , Yogesh Simmhan

Activations have become the primary memory bottleneck in large-batch LLM training. However, existing compression methods fail to exploit the spectral structure of activations, resulting in slow convergence or limited compression. To address…

Machine Learning · Computer Science 2026-02-27 Yanyi Li , Yimu Zhang , Cong Fang

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual grounding, establishing themselves as a general interface for various vision-language applications. This progress has driven the development of…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Tzu-Chun Chien , Chieh-Kai Lin , Shiang-Feng Tsai , Ruei-Chi Lai , Hung-Jen Chen , Min Sun

Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that…

By mimicking brain-like cognition and exploiting parallelism, hyperdimensional computing (HDC) classifiers have been emerging as a lightweight framework to achieve efficient on-device inference. Nonetheless, they have two fundamental…

Machine Learning · Computer Science 2022-04-04 Shijin Duan , Xiaolin Xu , Shaolei Ren