https://openreview.net/forum?id=fopzaE8J8p&referrer=%5Bthe%20profile%20of%20Mingzhe%20Du%5D(%2Fprofile%3Fid%3D~Mingzhe_Du1)
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning | OpenReview
To enhance the safety of VLMs, this paper introduces a novel reasoning-based VLM guard model dubbed GuardReasoner-VL. The core idea is to incentivize the guard...
vlsafeguardingviareinforcedreasoning