Any-to-any forward-dynamics cotraining for robot learning from video. FloMo fine-tunes the Wan 2.2 TI2V-5B video model (LoRA by default) to predict any subset of {robot action, future video, motion ...
A comprehensive, community-curated directory that aims to catalog and showcase the most outstanding AI-powered products. This index is not exhaustive, but rather a compilation of our research and ...