Wei Zhai

Reasoning segmentation requires models to ground complex, implicit textual queries into precise pixel-level masks. Existing approaches rely on a single segmentation token \<SEG\> , whose hidden state implicitly encodes both semantic reasoning and spatial localization, limiting the model’s ability...

Large Reasoning Models(LRMs) have achieved significant breakthroughs over prior large language models (LLMs), but they also entail greater potential safety risks. Existing alignment methods often remain at a shallow level of protection, making them insufficient to address deeper risks and strateg...