We focus on developing trustworthy and socially responsible AI systems. Our research spans the robustness, security, safety, and interpretability of AI systems, from traditional deep neural networks to modern large language models (LLMs), multimodal LLMs, and AI agents. We also explore interdisciplinary applications of trustworthy AI in critical domains, including healthcare, sustainable infrastructure, and cybersecurity.
Research
Research Directions
-
Safety and Security of LLMs and Multimodal AI
We study adversarial attacks, poisoning attacks, jailbreaks, and multimodal safety failures, and develop methods for failure discovery, robust learning, and proactive safeguards.
-
Trustworthy AI for Time-Series and Health Data
We develop reliable learning methods for temporal, physiological, and longitudinal data, with applications in digital health, healthcare, and digital twins.
-
Reliable Agentic and Multimodal Reasoning
We study reliable reasoning and interaction with multimodal data, external knowledge, and computational tools, including multi-agent and retrieval-augmented systems.
-
AI for Security and Resilient Systems
We explore how AI can support vulnerability discovery, security analysis, and resilient decision-making in cybersecurity and critical infrastructure.
Active Projects
-
Collaborative Research: Elements: AI-Agentic Digital Twin for Collaborative Building Auditing and Retrofit Simulation
NSF CSSI (2026–2029)
This project develops an interactive platform that integrates agentic AI, digital twins, building data, and simulation to support collaborative building auditing and retrofit planning. Our group investigates reliable multimodal information retrieval and reasoning for AI agents, enabling them to ground their decisions in heterogeneous building data and technical documents, reason across multiple sources, and produce accurate, traceable responses.
People
Mentored Students
- Xiaohuan Bi – Undergraduate at Renmin University of China
- Falong Fan – M.S. from The Chinese University of Hong Kong, Shenzhen
- Ruofan Mao – Master's student at UAB
Sponsors
Join Us 🙌
I’m looking for highly motivated PhD students to join my research group starting in Fall 2025 at CS@UAB.
Please check the Recruitment page for more details.
If you are interested, apply to the
CS PhD program
and mention my name in your application.
Additionally, send your CV and transcript to
xili.recruitment@gmail.com
with the subject [25Fall PhD Application].