以下为上游提供的源文稿,可能存在识别错误。
乔木转写是基于源文稿的中文提炼,不是逐字翻译。请核对原文中的人名、数字与观点。
选一篇,慢慢读
从左侧挑一篇,正文会在这里排成书页。
Recent advances in multimodal large language models have increased interest in interaction paradigms for video understanding. The evolution from offline to streaming and proactive interaction has gradually shifted models from passive responders toward more proactive agents that can decide when to answer. However, exist
阅读原文 · Lu Wang, Zhuoran Jin, Longxiang Wang, Junhong Chen, Yupu Hao, Yao Xu, Daojian Zeng, Yubo Chen, Kang Liu, Guang Liu, Jun Zhao
向阳乔木 · opencode-go/deepseek-v4.1-flash
这篇论文抓住了一个被忽略的动作: 模型在流式视频里不只会“等”和“答”,还应该会“问” 。 现有主动交互范式默认回答所需信息是完整的,模型只需决定何时开口。真实场景里信息经常不完整,来源可能是视频本身看不清,也可能是用户问得含糊。模型要么一直等下去,要么硬答出高幻觉内容。 作者提出,主动交互需要第三种动作:ask。让模型主动索要缺失信息。这个视角不难理解,但...