Jigang Wu — accepted AI-conference papers

2025

Improving Efficiency in Large Language Models via Extendable Block Floating Point Representation

Dongyang Li, Zeyang Li, Bosheng Liu, Jigang Wu

ACL 2025finding

Large language models (LLMs) have revolutionized natural language processing (NLP) tasks, yet their increasing size poses substantial challenges in terms of computational and memory resources. Block floating-point (BFP) arithmetic offers an effective solution by leveraging the strengths of both floa…

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

Weighted Graph Embedded Low-Rank Projection Learning for Feature Extraction

Zhuojie Huang, Shuping Zhao, Lunke Fei, Jigang Wu

ICASSP 2022accepted

Low-rank based methods have been widely adopted to structure preserving, when the projection matrix is learned for feature extraction. However, some dilemmas still exist that degrade the classification performance: 1) The local structure of the data is ignored; 2) the reconstructed data is not consi…

Cited by 0 Source ↗Scholar ↗