AI看视频该不该插话，终于有了个明白账
现在的AI看视频，是边看边决定要不要开口。但以前训练它时，整段视频只给一个总评分，导致它要么抢着说废话、要么该接话时装哑巴。这篇把评分拆到每一次「开口/沉默」的决策上：每次决定单独算账，还让「说话」和「继续看」在训练里权重一样，不因为话多话少被带偏。结果就是，AI更知道什么时候该插嘴、什么时候该闭嘴，废话少了，该补的跟进也来了。它不是你明天就能用上的东西，但这是AI从「看完再答」走向「边看边聊」的关键一步。
📄 原文摘要(英文)
Streaming video understanding requires models to repeatedly decide whether to respond or continue observing. Recently, Group Relative Policy Optimization (GRPO) has been applied to this setting, with existing approaches emphasizing reward design while retaining a single trajectory-level advantage across turns. Such shared credit can reinforce redundant replies after earlier successes and discourage useful follow-ups after earlier failures. We propose TurnWise, a turn-level GRPO framework that aligns learning with individual streaming decisions. TurnWise addresses the mismatch between trajectory-level feedback and turn-level interaction, promoting informative responses and reducing redundancy. Specifically, turn-level credit assignment uses silence-completed prefix scoring to construct group-relative advantages from each decision's remaining return, separating its learning signal from earlier rewards. Turn-mean policy optimization averages token losses within each turn and then across turns, giving response and waiting decisions equal weight regardless of output length. These complementary designs improve streaming policy learning without a learned critic or additional rollouts. Extensive experiments show our method outperforms prior RL approaches for streaming video understanding.