ECE's Wu Honored With Best Paper at IEEE Symposium
July 3, 2024
BATON ROUGE, LA – LSU Electrical and Computer Engineering Professor Hsiao-Chun Wu was recently honored by the Institute of Electrical and Electronics Engineers (IEEE) Broadcast Technology Society with the 2024 Best Paper Award at the IEEE International Symposium on Broadband Multimedia Systems and Broadcasting in Toronto, Canada.
The paper, titled “Fine-Tuning Optimization of Small Language Models: A Novel Graph-Theoretical Approach for Efficient Prompt Engineering,” was co-authored by Wu, who is also an IEEE Fellow; Venkata Gadiraju, LSU Ph.D. graduate in electrical engineering and computer science; Hao-Yu Tsai, Ph.D. student in the National Tsing Hua University Department of Electrical Engineering; Manali Singha, LSU Ph.D. graduate in computational system biology; Scott C.-H. Huang, professor in the National Tsing Hua University Department of Electrical Engineering; Guannan Liu, assistant professor in the San Jose State University Department of Applied Data Science (also an LSU Ph.D. graduate in electrical engineering and computer science); Shih Yu Chang, assistant professor of applied data science at San Jose University; and Yiyan Wu, professor in Western University’s Department of Electrical and Computer Engineering.
In recent years, large language models, or LLMs, have been widely applied in artificial intelligence (AI)-driven prompt engineering, such as question answering and text summarization functionalities. However, there is a growing interest in small language models, or SLMs, for resource-constrained, application-specific data mining. SLMs involve much fewer parameters than LLMs and offer advantages in terms of reduced carbon emission, short training times, and low computational complexity.
The paper details the research group’s work with SLMs by designing a new systematic approach to extract the semantic-, contextual-, and domain-relevant relationships among users’ prompts; extend the conventional clique-finding paradigm for training data reduction (TDR) and evaluate the approach using the GPT-2 model (a large language model by OpenAI); develop a time-complexity analysis for the new TDR scheme; and compare the new approach with the conventional model, showing the on-par performance and better-than-conventional-method performance using the BERTScore, a metric useful in evaluating the quality of text summary in relation to the original text.
Wu is the Michel B. Voorhies Professor in the LSU Division of Electrical and Computer Engineering. He earned his Ph.D. from the University of Florida, and his research interests include statistical learning on optimization, estimation and detection applications, embedded algorithms for digital signal processing, speech and image processing, and wireless communications.
Like us on Facebook (@lsuengineering) or follow us on X (formerly Twitter) and Instagram (@lsuengineering).
###
Contact: Joshua Duplechain
Director of Communications
225-578-5706
josh@lsu.edu
Latest College of Engineering News
- LSU Researchers Awarded $1.5 Million to Advance Worldwide Access to High-Performance ComputingSeptember 13, 2024data center The LSU researchers’ goal is to make high-performance computing more accessible across all computational platforms to a broader range of researchers and organizations—all to accelerate scientific research to solve global challenges.LSU researchers have been awarded a $1.5 million Pathways to Enable Open-Source Ecosystems, or POSE, grant from the National Science Foundation to advance the ecosystem surrounding HPX, a software library developed at LSU. Their goal is a fast and energy-efficient solution to increase worldwide access to high-performance computing. Lack of access and performance currently limits the success and usefulness of emerging technologies, such as AI and machine learning, and computational modeling in almost every field.
- LSU Electrical, Computer Engineering Professor Designs Intelligent Drone for Rescue OperationsSeptember 18, 2024BATON ROUGE, LA - The National Fire Protection Association estimates that one home fire-related death occurs in the U.S. every three hours and 14 minutes, and one home fire-related injury occurs every 53 minutes. These are numbers LSU Electrical and Computer Engineering Assistant Professor Xiangyu Meng hopes to change for the better through his design of an intelligent drone that will use thermal technology during rescue operations, particularly for firefighters.
- LSU, Integer Partner to Optimize U.S. Navy, Marine Corps OperationsSeptember 9, 2024BATON ROUGE, LA - A team of LSU researchers has been tasked with helping the U.S. Navy and Marine Corps make the transformation to Distributed Maritime Operations (DMO), which would allow the two military branches to move beyond traditional reliance on a few large vessels and instead emphasize a distributed network of smaller naval platforms that enhance presence and awareness in vital maritime regions.
- LSU Computer Science PhD Student Wins Pair of Best Paper AwardsSeptember 3, 2024BATON ROUGE, LA - Prior to this summer, LSU Computer Science Ph.D. student Taha Gharaibeh had never won a Best Paper award, which is typically given in recognition of the quality and impact of the published work.
- LSU Engineering, LSUHSC School of Dentistry Collaboration Illustrates Benefit to IndustryAugust 30, 2024BATON ROUGE, LA - Each year, 9 million people in the U.S. get braces. Whether it's to fix a bad bite or simply gain a more attractive smile, braces have almost become a rite of passage in Western culture. In an attempt to improve the effectiveness of bonding material used in braces, LSU Health Sciences Center (LSUHSC) School of Dentistry-Prosthodontics is collaborating with LSU's College of Engineering on three projects led by LSUHSC Digital Fabrication Center Director and LSU Petroleum Engineering Assistant Professor of Research Charles Taylor.
- LSU-Southern Cyber Project to Protect Nation’s Electric Vehicle Infrastructure, Build WorkforceAugust 22, 2024A collaborative team at LSU and Southern University has been awarded a $1.2 million grant from the National Science Foundation to address critical cybersecurity vulnerabilities in electric vehicle charging stations. Discovered by LSU cybersecurity expert Elias Bou-Harb and his team, these vulnerabilities pose significant risks, including the potential for hackers to access and exploit tens of thousands of EV charging stations connected to the power grid. This project not only aims to secure these systems but also to educate and train a more diverse cybersecurity workforce, leveraging the strengths of both universities.