5万小时人类视频，喂出机器人
机器人学操作，一直卡在数据：真机采集贵、慢、少。这篇把镜头对准人——第一人称视角拍下 5 万小时人干活的视频，配上手部动作和语言描述，全部开源。他们先只用人视频预训练，发现一条干净的规律：预训练数据每翻一倍，下游机器人成功率就按对数线性往上走，规模本身就能换来能力。只用这 5 万小时训出的模型，在仿真里做整理任务成功率 92.08%，换个随机光照背景掉到 68.88%。再把人类视频和机器人数据混着训，同一个任务在随机场景里从 68.88% 跳到 84.60%，真机上还出现了没训过的新行为：给它看一张没见过的目标图，它不改参数就调整动作去够。它不是你明天能装在家里的东西，但「人类视频是机器人数据的免费矿」这件事，从猜想变成了有曲线、有开源配方可复现的结论。
📄 原文摘要(英文)
Egocentric human video offers a scalable source of manipulation priors for robot learning, yet translating raw data scale into generalizable robot policies demands rigorous data curation and training recipes. We introduce Open-HumanScale, the first fully open recipe for scaling egocentric pretraining to 50,000 hours, anchored by Open-HumanScale-50K---a curated egocentric video corpus densely annotated with hand motion and natural language. Leveraging this corpus, we systematically investigate pure human pretraining via closed-loop simulation evaluations and uncover an empirical log-linear scaling law linking pretraining data hours to downstream robot success rates. Grounded in these findings, we develop HumanWAM-Vanilla, a world--action model pretrained exclusively on 50k hours of egocentric human video. Upon robot post-training, HumanWAM-Vanilla reaches 92.08% success on RoboTwin 2.0 Clean2Clean and 68.88% on Clean2Random, alongside a 14.17% mean success rate and a 19.00 mean progress score on RoboDojo. To push the capability frontier further, we explore joint human--robot pretraining with HumanWAM-Goal, a visual-goal-conditioned world--action model. Hybrid data scaling unlocks broad zero-shot generalization across both simulation and physical benchmarks, propelling post-trained RoboTwin 2.0 performance to new state-of-the-art levels: 92.70% on Clean2Clean and a substantial leap to 84.60% on Clean2Random. On physical robots, HumanWAM-Goal further exhibits emergent embodied in-context learning, dynamically adapting its manipulation behavior to unseen visual goals without parameter updates. To support reproducible scaling research in embodied AI, we open-source the Open-HumanScale-50K corpus, data curation and pretraining pipelines, alongside the pretrained and post-trained HumanWAM checkpoints, inference code, and simulation evaluation suites.