Ph.D. Candidate in Computer Science | Vanderbilt University

[Trustworthy AI] [AI & NLP] [Social Good]
Download CV

About Me

Zirong Chen

Hello! My name is Zirong (Rex) Chen (陈子荣), currently pursuing a Ph.D. in Computer Science at Vanderbilt University under Professor Meiyi Ma's supervision. My research focuses on AI Safety and Trustworthy AI, with particular emphasis on Natural Language Processing (NLP), reliable AI systems for critical applications, and trustworthy AI-driven solutions for Smart Cities and emergency response. I earned my bachelor's degree (B.E. in Computer Engineering) in China and my master's degree (M.S. in Computer Science) at Georgetown University. I am also a former basketball player in high school and college.

Education

News

Publications
Awards & Grants
Events & Talks
Product Launches
Academic Service
Updates

Research Projects

Logic-informed Call-taking Performance Debriefing

We develop trustworthy AI systems that decompose LLM runtime into modularized function calls enhanced with Signal Temporal Logic, ensuring reliable and interpretable performance evaluation for safety-critical call-taking scenarios.

Keywords: Trustworthy AI, AI Safety, Reliable LLMs

Learn More LogiDebrief system architecture showing LLM integration with Signal Temporal Logic for automated debriefing

Customized Emergency Response Training

Collaborating with Metro Nashville Department of Emergency Communications, we develop Angie/SimER - a safety-critical AI system that provides reliable, trustworthy simulation environments for call-taker training in high-stakes emergency response scenarios.

Keywords: Safety-Critical AI, Trustworthy LLMs, Reliable Systems

Learn More SimER system overview showing AI-driven simulation environment for call-taker training with Metro Nashville DEC

Trustworthy Emergency Response Systems

We develop reliable AI systems with built-in safety guarantees that enhance emergency response decision-making. Our trustworthy machine learning approaches ensure robust performance in critical situations while maintaining transparency and accountability.

Keywords: AI Safety, Trustworthy ML, Reliable Decision Systems

Learn More Auto311 system diagram showing confidence-guided automated processing for non-emergency calls

Adaptable City Knowledge

The Adaptable City Knowledge project aims to create a dynamic, data-driven platform that helps cities respond to evolving challenges. From traffic management to disaster preparedness, this initiative fosters collaboration between city officials, businesses, and residents to promote resilience.

Keywords: AI/ML, NLP, Life-long Learning

Learn More CitySpec system architecture for intelligent requirement specification in smart cities with formal verification

Publications

[IJCAI-25] (Oral Spotlight - 13%) LogiDebrief: A Signal-Temporal Logic based Automated Debriefing Approach with Large Language Models Integration
[AAAI-25] (Oral Spotlight - 4.9%) Sim911: Towards Effective and Equitable 9-1-1 Dispatcher Training with an LLM-Enabled Simulation
[AAAI-24] (Oral Spotlight - 6%) Auto311: A Confidence-Guided Automated System for Non-emergency Calls
[Pervasive and Mobile Computing] CitySpec with shield: A secure intelligent assistant for requirement formalization
[IEEE SmartComp 22] (Best Paper Finalist) Cityspec: An intelligent assistant system for requirement specification in smart cities
[IEEE SmartComp 22] An intelligent assistant for converting city requirements to formal specification

Contact

Email: zirong.chen AT vanderbilt.edu
Office: Institute for Software Integrated Systems, Vanderbilt University
Address: 1025 16th Ave S, Nashville, TN 37212
Links: Google Scholar | ORCID | LinkedIn

Visitor Map