Dyna Robotics把100万小时人类视频喂给机器人模型，搞出了Dyna-2，还验证了缩放定律能跨界到机器人数据，看它怎么做到跨实体泛化挺有意思。
Dyna Robotics推出世界动作模型Dyna-2，预训练数据超过100万小时的第一人称人类视频。技术报告展示了在人类数据上至1M小时的缩放定律，并首次将该定律迁移到未见过的机器人数据。实验还表明，视频联合训练能推动跨实体泛化。该模型旨在让机器人从人类行为中学习动作执行。
Dyna Robotics Introduces Dyna-2: A World-Action Model Pre-Trained on 1 Million Hours of Human Video
Dyna Robotics has released Dyna-2, a world-action model pre-trained on more than one million hours of egocentric human video. The technical report establishes three results: a scaling law on human data to 1M hours, the first transfer of that law to unseen robot data, and evidence that video co-training drives cross-embodiment generalization. The post Dyna Robotics Introduces Dyna-2: A World-Action Model Pre-Trained on 1 Million Hours of Human Video appeared first on MarkTechPost .