arXiv · cs.AI · Chuang Yu, Xuefei Ma, Yuanhao Feng, Wuxiong Zeng, Bo Wang, Minghong Cai, Dongming Wu, Fei Zhou, Chen Tang, Wenwen Tong, Lewei Lu, Xiangyu Yue · 10 小时前模型评分35
ReState：面向多模态大模型MLLM的统一迭代推理框架
From Stages to States: Unified Iterative Reasoning for MLLMs
导读
研究者提出 ReState，一个把多模态推理从按预设阶段分别训练改为在共享状态空间中动态转移的统一迭代推理框架，包含统一推理状态建模（URSM）与闭环推理状态学习（CRSL）两部分。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “To address these limitations, we propose ReState, a unified iterative reasoning framework that reformulates multimodal reasoning from a stage-driven pipeline into a state-driven dynamic process.”
- “Our data and code are available at this https URL”
来源：arXiv · cs.AI · arxiv.org