Rui Zhou

The paper analyzes protracted vulnerabilities (PCVEs) in open-source projects and proposes DeeptraVul, an enhanced detection approach that significantly improves vulnerability coverage by integrating multiple development artifacts and an LLM.

MACReD introduces a hierarchical multi-agent framework that achieves state-of-the-art performance in parsing complex chemical reaction diagrams by coordinating specialized agents for perception and global reasoning.

ESPO is a novel reinforcement learning algorithm that detects trajectory failure in large language models and terminates rollouts early, significantly improving performance on mathematical reasoning benchmarks while reducing computational cost.