1
iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning
用强化学习让多模态大模型内化视觉推理能力，突破传统提示依赖，实现更可靠的图文理解。
arXiv:2605.31096v1 Announce Type: new Abstract: While visually grounded Chain-of-Thought (CoT) has emerged as a promising paradigm to enhance fine-gra…