English
Related papers

Related papers: SparseOptimizer: Sparsify Language Models through …

200 papers

With the dramatically increased number of parameters in language models, sparsity methods have received ever-increasing research focus to compress and accelerate the models. While most research focuses on how to accurately retain…

Artificial Intelligence · Computer Science 2022-05-24 Yuchao Li , Fuli Luo , Chuanqi Tan , Mengdi Wang , Songfang Huang , Shen Li , Junjie Bai

Researchers are exploring novel computational paradigms such as sparse coding and neuromorphic computing to bridge the efficiency gap between the human brain and conventional computers in complex tasks. A key area of focus is neuromorphic…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-01 Soufiyan Bahadi , Eric Plourde , Jean Rouat

Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods merely exploit a model's inherent sparsity and thus plateau at…

Machine Learning · Computer Science 2026-03-02 Feng Chen , Yefei He , Lequan Lin , Chenhui Gou , Jing Liu , Bohan Zhuang , Qi Wu

Language diversity presents a significant challenge in speech-to-text (S2T) tasks, such as automatic speech recognition and translation. Traditional multi-lingual multi-task training approaches aim to address this by jointly optimising…

Sound · Computer Science 2025-07-09 Qiuming Zhao , Guangzhi Sun , Chao Zhang

With the rapid growth in the scale of pre-trained foundation models, parameter-efficient fine-tuning techniques have gained significant attention, among which Adapter Tuning is the most widely used. Despite achieving efficiency, it still…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Qizhe Zhang , Bocheng Zou , Ruichuan An , Jiaming Liu , Shanghang Zhang

Model merging has emerged as a compelling data-free paradigm for multi-task learning, enabling the fusion of multiple fine-tuned models into a single, powerful entity. A key technique in merging methods is sparsification, which prunes…

Computation and Language · Computer Science 2025-08-11 Yingfeng Luo , Dingyang Lin , Junxin Wang , Ziqiang Xu , Kaiyan Chang , Tong Zheng , Bei Li , Anxiang Ma , Tong Xiao , Zhengtao Yu , Jingbo Zhu

In this paper, we review state-of-the-art methods for feature selection in statistics with an application-oriented eye. Indeed, sparsity is a valuable property and the profusion of research on the topic might have provided little guidance…

Methodology · Statistics 2021-11-08 Dimitris Bertsimas , Jean Pauphilet , Bart Van Parys

Sparse codes in neuroscience have been suggested to offer certain computational advantages over other neural representations of sensory data. To explore this viewpoint, a sparse code is used to represent natural images in an optimal control…

Machine Learning · Computer Science 2021-01-08 Peter N. Loxley

The pre-trained language models like BERT, though powerful in many natural language processing tasks, are both computation and memory expensive. To alleviate this problem, one approach is to compress them for specific tasks before…

Computation and Language · Computer Science 2020-10-12 Lu Hou , Zhiqi Huang , Lifeng Shang , Xin Jiang , Xiao Chen , Qun Liu

In distributed optimization for large-scale learning, a major performance limitation comes from the communications between the different entities. When computations are performed by workers on local data while a coordinator machine…

Optimization and Control · Mathematics 2020-06-26 Dmitry Grishchenko , Franck Iutzeler , Jérôme Malick , Massih-Reza Amini

Activation sparsity refers to the existence of considerable weakly-contributed elements among activation outputs. As a prevalent property of the models using the ReLU activation function, activation sparsity has been proven a promising…

Machine Learning · Computer Science 2025-01-08 Chenyang Song , Xu Han , Zhengyan Zhang , Shengding Hu , Xiyu Shi , Kuai Li , Chen Chen , Zhiyuan Liu , Guangli Li , Tao Yang , Maosong Sun

Existing speaker diarization systems typically rely on large amounts of manually annotated data, which is labor-intensive and difficult to obtain, especially in real-world scenarios. Additionally, language-specific constraints in these…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-13 Phat Lam , Lam Pham , Truong Nguyen , Dat Ngo , Thinh Pham , Tin Nguyen , Loi Khanh Nguyen , Alexander Schindler

Current compiler optimization reports often present complex, technical information that is difficult for programmers to interpret and act upon effectively. This paper assesses the capability of large language models (LLM) to understand…

Programming Languages · Computer Science 2025-06-16 Peter Pirkelbauer , Chunhua Liao

Compressive sensing claims that the sparse signals can be reconstructed exactly from many fewer measurements than traditionally believed necessary. One of issues ensuring the successful compressive sensing is to deal with the…

Information Theory · Computer Science 2009-03-31 Lianlin Li , Fang Li

The increasing size of deep neural networks (DNNs) necessitates effective model compression to reduce their computational and memory footprints. Sparsity and quantization are two prominent compression methods that have been shown to reduce…

Large language models (LLMs) exhibit substantial performance disparities across languages, particularly between high- and low-resource settings. We propose a framework for improving performance in underrepresented languages while preserving…

Computation and Language · Computer Science 2026-02-05 Daniil Gurgurov , Tanja Baeumel , Josef van Genabith , Simon Ostermann

In recent years, there has been a flurry of research in deep neural network pruning and compression. Early approaches prune weights individually. However, it is difficult to take advantage of the resulting unstructured sparsity patterns on…

Machine Learning · Computer Science 2020-08-28 Ziheng Wang

Dense large language models(LLMs) face critical efficiency bottlenecks as they rigidly activate all parameters regardless of input complexity. While existing sparsity methods(static pruning or dynamic activation) address this partially,…

Computation and Language · Computer Science 2025-02-27 Yiheng Yang , Yujie Wang , Chi Ma , Lei Yu , Emmanuele Chersoni , Chu-Ren Huang

In recent years, BERT has made significant breakthroughs on many natural language processing tasks and attracted great attentions. Despite its accuracy gains, the BERT model generally involves a huge number of parameters and needs to be…

Computation and Language · Computer Science 2021-02-19 Cheng Yang , Shengnan Wang , Yuechuan Li , Chao Yang , Ming Yan , Jingqiao Zhang , Fangquan Lin

Existing approaches to increasing the effective depth of Transformers predominantly rely on parameter reuse, extending computation through recursive execution. Under this paradigm, the network structure remains static along the training…

Computation and Language · Computer Science 2026-04-17 Yao Chen , Yilong Chen , Yinqi Yang , Junyuan Shang , Zhenyu Zhang , Zefeng Zhang , Shuaiyi Nie , Shuohuan Wang , Yu Sun , Hua Wu , HaiFeng Wang , Tingwen Liu