Hong Jia

ChainCaps introduces a novel runtime capability budgeting system that prevents 'permission laundering' in complex tool-using agents, significantly reducing attack success rates while maintaining benign functionality.

VitalAgent is a novel tool-augmented agentic framework that significantly improves physiological monitoring from wearable health data by enabling both reactive question answering and proactive, long-term signal analysis.

The paper introduces Pocket-Dentist, an efficiency-aware benchmark and model that demonstrates that compact, smaller Vision-Language Models (VLMs) can outperform larger models in accuracy while drastically reducing computational cost for on-device dental image understanding.

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, exploitable security vulnerabilities.

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, unaddressed security vulnerabilities.