← 研踪 PaperTrailCVF · CVPR 2026:cvf:462fd4de523fc59fd8826429c63e5d70 · 记录 #1
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
Liu, ShumingZhuge, MingchenZhao, ChangshengChen, JunWu, LemengLiu, ZechunZhu, ChenchenCai, ZhipengZhou, ChongLiu, HaozheChang, ErnieSuri, SakshamXu, HongyuQian, QiWen, WeiVaradarajan, BalakrishnanLiu, ZhuangXu, HuBordes, FlorianKrishnamoorthi, RaghuramanGhanem, BernardChandra, VikasXiong, Yunyang 来源日期(仅到年份) 2026
来源记录日期 2026
雷达观测 2026-11-05 00:20
摘要
Chain-of-thought (CoT) reasoning has emerged as a powerful tool for multimodal large language models on video understanding tasks. However, its necessity and advantages over direct answering remain underexplored. In this paper, we first demonstrate that for RL-trained video models, direct answering often matches or even surpasses CoT performance, despite CoT producing step-by-step analyses at a higher computational cost. Motivated by this, we propose VideoAuto-R1, a video understanding framework that adopts a reason-when-necessary strategy. During training, our approach follows a Thinking Once, Answering Twice paradigm: the model first generates an initial answer, then performs reasoning, and finally outputs a reviewed answer. Both answers are supervised via verifiable rewards. During inference, the model uses the confidence score of the initial answer to determine whether to proceed with reasoning. Across video QA and grounding benchmarks, VideoAuto-R1 achieves state-of-the-art accuracy with significantly improved efficiency, reducing the average response length by 3.3x, eg., from 149 to just 44 tokens. Moreover, we observe a low rate of thinking-mode activation on perception-oriented tasks, but a higher rate on reasoning-intensive tasks. This suggests that explicit language-based reasoning is generally beneficial but not always necessary.
论文发现出处
这些页面提供论文线索,不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
Chain-of-thought (CoT) reasoning has emerged as a powerful tool for multimodal large language models on video understanding tasks. However, its necessity and advantages over direct answering remain underexplored. In this paper, we first demonstrate that for RL-trained video models, direct answering often matches or even surpasses CoT performance, despite CoT producing step-by-step analyses at a higher computational cost. Motivated by this, we propose VideoAuto-R1, a video understanding framework that adopts a reason-when-necessary strategy. During training, our approach follows a Thinking Once, Answering Twice paradigm: the model first generates an initial answer, then performs reasoning, and finally outputs a reviewed answer. Both answers are supervised via verifiable rewards. During inference, the model uses the confidence score of the initial answer to determine whether to proceed with reasoning. Across video QA and grounding benchmarks, VideoAuto-R1 achieves state-of-the-art accuracy with significantly improved efficiency, reducing the average response length by 3.3x, eg., from 149 to just 44 tokens. Moreover, we observe a low rate of thinking-mode activation on perception-oriented tasks, but a higher rate on reasoning-intensive tasks. This suggests that explicit language-based reasoning is generally beneficial but not always necessary.
查看此版本解读 →查看此版本原文 ↗