2 papers
cs.CV2026
Solaris: Building a Multiplayer Video World Model in Minecraft
Georgy Savva, Oscar Michel, Daohan Lu +6
Existing action-conditioned video generation models (video world models) are limited to single-agent perspectives, failing to capture the multi-agent interactions of real-world env…
cs.RO2024
Bridging the Human to Robot Dexterity Gap through Object-Oriented Rewards
Irmak Guzey, Yinlong Dai, Georgy Savva +2
Training robots directly from human videos is an emerging area in robotics and computer vision. While there has been notable progress with two-fingered grippers, learning autonomou…