让AI看视频学得更快：把标准答案直接喂进去
训练AI看视频理解世界，通常得让它自己试错、再给奖励，像教小孩做题只告诉他分数。这篇发现一个被忽略的捷径：每个训练样本的标注本身就是标准答案，直接把它当成一次“满分示范”混进AI的练习里，比让它瞎猜高效得多。但直接塞会出问题——满分示范把平均分拉高，AI反而觉得自己的正确答案“不够好”。研究者设计了一个巧妙的算法，把示范和AI自己的尝试分开算分，再砍掉没用的练习，训练速度比传统方法快一倍多，效果在视频分割、目标追踪等任务上全面超过之前的顶尖模型，而且不需要昂贵的“思考链”步骤，9B参数的模型处理一帧从4.78秒降到0.13秒。这不是你明天能用的工具，但它意味着AI理解视频的成本正在快速下降，未来视频问答、自动驾驶、机器人看世界都会因此更聪明、更便宜。
📄 原文摘要(英文)
Multimodal large language models (MLLMs) have become a prevailing paradigm for unified video perception. However, post-training on large multi-task datasets remains challenging, as existing reinforcement learning methods sample on-policy groups with few high-quality rollouts even with costly chain-of-thought (CoT) generation. In this paper, we study the sample efficiency and scalability of RL post-training for video MLLMs and introduce OraRL. We identify an overlooked role for annotations: Beyond scoring rollouts, each can enter its on-policy group as an oracle rollout, a direct positive optimization target. Direct oracle integration, however, is nontrivial: a high-reward oracle raises the group baseline and inverts otherwise positive policy advantages, a failure we term advantage inversion. At the core of OraRL is a decoupled advantage estimator: policy rollouts determine an oracle-free baseline, while the oracle-policy gap modulates both a directional gain and a separate detached oracle advantage. Sign-balanced pruning improves efficiency: by retaining only the oracle and the strongest rollouts of each sign, OraRL requires just 2.2x the step time of SFT, less than half the 4.9x required by GRPO with CoT. OraRL scales with model size and data, surpassing its backbone from 0.8B to 9B and GRPO up to 100k prompts. Without chain-of-thought, Video-ORA-9B decodes in 130 ms instead of 4,780 ms. Compared with the respective prior best models, it raises temporal mIoU from 62.5 to 66.0, tracking AO from 73.0 to 78.2, segmentation from 64.3 to 70.4, and the three-benchmark spatial-intelligence macro average from 51.0 to 56.1; on VSI-Bench, it scores 73.1 against 55.0 for GPT-5 and 55.1 for Gemini-3-Pro.