About

Li-C. Wang is a professor in the Department of Electrical and Computer Engineering at UC Santa Barbara. His research interests include Artificial Intelligence for Design and Test, Data Analysis, and Machine Learning. He is associated with the Intelligent Engineering Assistant Lab. His contact information includes a phone number, email, and office location in Harold Frank Hall. Further details about his professional background, research contributions, and academic activities are not provided in the available page text.

Research topics

• Artificial Intelligence
• Computer Science
• Machine Learning
• Engineering
• Electrical engineering
• Medicine
• Virology
• Genetics
• Biology
• Operating system

Selected publications

• IEA-Plugin: An AI Agent Reasoner for Test Data Analytics

  2025-09-20

  articleSenior author

  This paper introduces IEA-plugin, a novel AI agent-based reasoning module developed as a new front-end for the Intelligent Engineering Assistant (IEA). The primary objective of IEA-plugin is to utilize the advanced reasoning and coding capabilities of Large Language Models (LLMs) to effectively address two critical practical challenges: capturing diverse engineering requirements and improving system scalability. Built on the LangGraph agentic programming platform, IEA-plugin is specifically tailored for industrial deployment and integration with backend test data analytics tools. Compared to the previously developed IEA-Plot (introduced two years ago), IEA-plugin represents a significant advancement, capitalizing on recent breakthroughs in LLMs to deliver capabilities that were previously unattainable.

  PublisherDOI

• LLMs Meet Post-Silicon Test Engineering: A New Era (Invited)

  2025-06-22

  article1st authorCorresponding

  The transformative power of Large Language Models (LLMs) is reshaping the role of AI in post-silicon test engineering. This paper summarizes our experience in leveraging LLMs to develop AI agents specifically tailored for this domain. Central to our approach is a two-stage process: first, we utilize the reasoning capabilities of LLMs to systematically interpret user queries; second, we invoke a grounding process to execute tasks as directed by these queries. This grounding ensures seamless integration of the LLM with existing test engineering infrastructure, enabling the AI agent to autonomously perform tasks within an established framework. Using the Intelligent Engineering Assistant (IEA) as a case study, we demonstrate how domain-specific, LLM-powered AI agents can automate critical aspects of test engineering, and highlight the potential of LLMs to revolutionize post-silicon test engineering through intelligent, context-aware automation.

  PublisherDOI

• IEA-Plugin: An AI Agent Reasoner for Test Data Analytics

  ArXiv.org · 2025-04-14

  preprintOpen accessSenior author

  This paper introduces IEA-plugin, a novel AI agent-based reasoning module developed as a new front-end for the Intelligent Engineering Assistant (IEA). The primary objective of IEA-plugin is to utilize the advanced reasoning and coding capabilities of Large Language Models (LLMs) to effectively address two critical practical challenges: capturing diverse engineering requirements and improving system scalability. Built on the LangGraph agentic programming platform, IEAplugin is specifically tailored for industrial deployment and integration with backend test data analytics tools. Compared to the previously developed IEA-Plot (introduced two years ago), IEA-plugin represents a significant advancement, capitalizing on recent breakthroughs in LLMs to deliver capabilities that were previously unattainable.

  PublisherOA PDFDOI

• LLM-Assisted Analytics in Semiconductor Test (Invited)

  2024-09-03 · 1 citations

  articleOpen access1st authorCorresponding

  The emergence of Large Language Models (LLMs) has impacted our perspective on applying Machine Learning (ML) in semiconductor test. This paper shares our experience in leveraging the power of LLMs to build an AI agent for test data analytics. We advocate for an end-to-end approach where the Knowledge Graph (KG) plays a central role. Using wafermap analytics as an example, we highlight the key ideas behind developing the LLM-assisted AI agent named IEA-Plot, and discuss its practical applications.

  PublisherOA PDFDOI

• Simulation Inspection Technology for Surface Characteristics of High-Quality Strips

  International Journal of Simulation Modelling · 2024-08-31 · 1 citations

  articleOpen access

  To address the challenge of high rejection rates due to surface quality defects that are hard to detect with the naked eye, a comprehensive model was developed for detecting such defects and implemented a full-fledged equipment and system for surface quality inspection.Specifically, a targeted comprehensive model was formulated to identify three types of plate and strip surface quality defects.Furthermore, the latest hardware equipment and an advanced unsupervised self-learning algorithm were integrated into the detection system to enhance the identification and classification of these surface quality defects.The results demonstrate an improvement in the comprehensive detection rate and classification accuracy of surface defects from 96 % and 91 % to 98 % and 95 %, respectively.Moreover, the qualified rate of finished products has increased from 94 % to 99 %, leading to improved accuracy in defect detection and a significant decrease in false alarm rates.These findings provide a solid foundation for significantly reducing material waste and enhancing the overall quality of the production process.

  PublisherDOI

• Oracle-Checker Scheme for Evaluating a Generative Large Language Model

  arXiv (Cornell University) · 2024-05-06

  preprintOpen access

  This work presents a novel approach called oracle-checker scheme for evaluating the answer given by a generative large language model (LLM). Two types of checkers are presented. The first type of checker follows the idea of property testing. The second type of checker follows the idea of program checking. Their applications are demonstrated in two separate contexts, entity extraction and paraphrase decision, respectively.

  PublisherOA PDFDOI

• LLM-Assisted Analytics in Semiconductor Test (Invited)

  2024-09-09 · 2 citations

  article1st authorCorresponding

  The emergence of Large Language Models (LLMs) has impacted our perspective on applying Machine Learning (ML) in semiconductor test. This paper shares our experience in leveraging the power of LLMs to build an AI agent for test data analytics. We advocate for an end-to-end approach where the Knowledge Graph (KG) plays a central role. Using wafermap analytics as an example, we highlight the key ideas behind developing the LLM-assisted AI agent named IEA-Plot, and discuss its practical applications.CCS Concepts• Hardware → Hardware test; • Computing methodologies → Artificial intelligence.

  PublisherDOI

• WM-Graph: Graph-Based Approach for Wafermap Analytics

  2024-11-03 · 3 citations

  articleSenior author

  This paper introduces WM-Graph, a novel approach designed for flexible analytics of wafermaps. The key concept behind WM-Graph is the construction of a wafermap graph, where individual wafermaps are connected if they exhibit semi-equivalence. This graph-based structure allows a wide range of analytics to be performed using established graph algorithms. Unlike traditional multi-class classification methods, WM-Graph enables more versatile analyses, making it possible to answer complex, practical questions that would otherwise be difficult to address. We explain the technical innovations that underpin the WM-Graph approach and demonstrate how to perform certain analytical tasks with simple graph operations. The effectiveness of the WM-Graph approach is validated through experiments using the public WM-811K dataset and a proprietary dataset from a recent production line.

  PublisherDOI

• Welcome Message ITC 2023

  2023-10-07

  articleOpen access1st authorCorresponding

  This volume contains the papers presented at the 2023 International Test Conference, held from October 10 - 12 at the Disneyland Hotel, Anaheim California. ITC is the world's premier conference dedicated to electronic test. This year's ITC continued with its mission to play a unique role as an information sharing forum, where the wide range of its offerings allows ITC participants to learn, network and conduct business. This year's program included a top-notch technical program, vibrant exhibitors, informationpacked tutorials, interactive technical panels, three focused workshops, as well as the all-important networking that these events provide. The technical program was designed to optimize personal interactions on all levels.

  PublisherOA PDFDOI

• Pan-viral serology defines hepatocellular carcinoma's response to immunotherapy

  HPB · 2023-01-01

  articleOpen access
  PublisherOA PDFDOI

Recent grants

• Statistical Tools and Methodologies for Timing Validation and Silicon Debug

  NSF · $275k · 2006–2009

• SHF: Small: Perception-Based Analytics For Semiconductor Production and Test Data

  NSF · $461k · 2020–2024

• SHF: Small: End-To-End Test Data Analytics For Automotive Chip Production Lines

  NSF · $400k · 2016–2020

Frequent coauthors

• Cheng‐Wen Wu

  Xingtai People's Hospital

  99 shared

• Kuen-Jong Lee

  National Cheng Kung University

  99 shared

• Magdy S. Abadir

  Norwegian University of Science and Technology

  69 shared

• Kwang‐Ting Cheng

  University of Hong Kong

  65 shared

• Xiaowei Li

  Wuhan Botanical Garden

  36 shared

• Xiaowei Li

  Chalmers University of Technology

  36 shared

• Y. Zorian

  Synopsys (United States)

  26 shared

• Xiaowei Li

  26 shared