Tag
Microsoft Mage Team presents Mage-VL-Cowork, a full training recipe (data synthesis from evolved harnesses, multi-stage SFT, and online hybrid RL) for learning hybrid computer use, with the 4B model achieving strong results on OSWorld-Verified relative to its size.
SceneMosaic combines learned image priors with vision-language agents to efficiently generate diverse, physically valid indoor scenes, achieving a 24x speedup and improved physical validity over existing methods.