Publications: 'SecCodePLT: A Unified Platform for Evaluating the Security of Code GenAI', NeurIPS 2025; 'Owl: Optimized workforce learning for general multi-agent assistance in real-world task automation', NeurIPS 2025; Awards: July 2025, one paper accepted to COLM 2025; February 2025, team (ForesAIght) won 1st place in safety track of Berkeley LLM Agents Hackathon; September 2024, received UCSB Research Excellent Award; July 2024, received FAR AI Research Grant to support research from 2024-2025.
Research Experience
June to August 2025, Research Scientist at Virtue AI, working on agent security; April 1 to June 13, 2025, Intern at virtue.ai, working on code guardrails for LLMs.
Education
PhD: University of California, Santa Barbara, Department of Computer Science, advised by Prof. Wenbo Guo; Bachelor's: Renmin University of China, Statistics, advised by Prof. Hongteng Xu.
Background
Research Interests: AI security and AI for security. Field: Computer Science.