Selected Projects
GRPO Vulnerability detection featured image
GRPO

GRPO Vulnerability detection

We adapt Group Relative Policy Optimization (GRPO) for software vulnerability detection, using rule-based rewards (no value function, no learned reward model).

GTPO featured image
GRPO

GTPO

The official implementation of GTPO (Group-relative Trajectory-based Policy Optimization), a novel method for stable and effective policy optimization in Large Language Models …