mimic-video/mimic-video

SUMMARY

Video-Action Models extend robot control capabilities beyond vision-language approaches by learning from video demonstrations. The mimic-video framework enables more generalizable robotic manipulation through direct video-to-action mapping. #robotics #ml #cv

Get research like this, matched to your field

Distill AI tracks arXiv, Nature, NeurIPS, CVPR, GitHub, HuggingFace and more — then surfaces the papers that matter to you, every morning. Track any custom topic, get 2-sentence summaries, and chat with any paper.