Boyuan Chen

The paper introduces RAVEN, a Retrieval-Augmented Vulnerability Exploration Network, which uses LLM agents and RAG to automatically generate comprehensive, structured vulnerability analysis reports for vulnerable code.

The paper introduces MiraBench, a new benchmark that evaluates the action-conditioned reliability of robotic world models, finding that visual fidelity is insufficient and that optimism bias is a pervasive issue across current systems.

The paper introduces and demonstrates that leveraging dynamic symmetry—the uniformity of attainable center-of-mass accelerations—significantly enhances a robot's agility, robustness, and multifunctionality across various challenging environments.