Hao Wei
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
SkillAttack is a red-teaming framework that dynamically tests the exploitability of latent vulnerabilities in LLM agent skills using adversarial prompting, demonstrating that even benign skills pose significant security risks.
RiskFlow is a novel framework that generates realistic and safety-critical multi-agent traffic scenarios by reformulating trajectory generation as a single-pass transport problem in the action space.
Introduces Looped World Models, a looped architecture for world modelling that iteratively refines latent environment states for up to 100x parameter efficiency.
The authors redesigned the symbolic backend of a SLOG test system using CCG directed types and achieved better performance than the previous SOTA.