insight-o3-multimodal

【设计与创意】Enable VLMs to perform generalized visual search—locating relational, fuzzy, and conceptual regions from free-form language descriptions. Introduces O3-Bench benchmark with high-density composite charts/maps, uses RL-trained vSearcher for spatial localization, improving frontier models (GPT-5-mini 39%→61.5%) without architecture changes.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准