iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning 文章

ArXiv CS.CV2026-06-01NEWSen作者: Chang-Bin Zhang, Yujie Zhong, Qiang Zhang, Kai Han
查看原文 →
关系图谱

iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning · 相关技术

相关技术

Multimodal Large Language Models (MLLMs)Internalizing Visually Grounded ReasoningTextual CoTchain-of-thoughtVisually Grounded Chain-of-Thought