← 研踪 PaperTrailarXiv:2611.26478 · v1
SHUSH: Emission-Aware Reward Design for Proactive Video Assistants
首次提交 2026-11-20 01:38
版本更新 2026-11-20 01:38
雷达观测 2026-11-20 12:52
摘要
Proactive video assistants must decide not only what to say, but also when to speak. Existing reinforcement-learning objectives can reward timely, correct responses without accounting for response volume, thereby encouraging unnecessary or repeated emissions. We identify this failure mode in MMDuet2, whose proactive area-under-the-curve (PAUC) reward promotes timely responses but does not price the number of emissions. We show analytically that this makes additional responses weakly penalized or effectively free, systematically encouraging over-emission. We then propose an emission-aware F1 reward for interval-valued annotations, using exclusive span--emission matching to price false emissions and missed spans. Under MMDuet2's training recipe, our policy on the visual subset of OmniPro replies 2.5x less often than MMDuet2 while raising timing F1 from 0.259 to 0.396 and content-aware F1 from 0.103 to 0.154; a more conservative variant cuts replies by 82.5% and raises precision from 0.161 to 0.418. On ProactiveVideoQA, the same reward adds replies where the baseline is nearly silent, and PAUC ranks a heavily over-emitting policy second despite near-last F1, because it is insensitive to response count. Our results indicate that proactive assistants should be trained and evaluated with objectives that price emissions.
作者备注:under review at ICASSP
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-20 01:38 · 最新观测版本
SHUSH: Emission-Aware Reward Design for Proactive Video Assistants
Proactive video assistants must decide not only what to say, but also when to speak. Existing reinforcement-learning objectives can reward timely, correct responses without accounting for response volume, thereby encouraging unnecessary or repeated emissions. We identify this failure mode in MMDuet2, whose proactive area-under-the-curve (PAUC) reward promotes timely responses but does not price the number of emissions. We show analytically that this makes additional responses weakly penalized or effectively free, systematically encouraging over-emission. We then propose an emission-aware F1 reward for interval-valued annotations, using exclusive span--emission matching to price false emissions and missed spans. Under MMDuet2's training recipe, our policy on the visual subset of OmniPro replies 2.5x less often than MMDuet2 while raising timing F1 from 0.259 to 0.396 and content-aware F1 from 0.103 to 0.154; a more conservative variant cuts replies by 82.5% and raises precision from 0.161 to 0.418. On ProactiveVideoQA, the same reward adds replies where the baseline is nearly silent, and PAUC ranks a heavily over-emitting policy second despite near-last F1, because it is insensitive to response count. Our results indicate that proactive assistants should be trained and evaluated with objectives that price emissions.
查看此版本解读 →查看此版本原文 ↗