Jinghuan Shang (@jsfiredrice)
2024-09-04 | โค๏ธ 148 | ๐ 22
CoRL2024 accepted!! Theia: Distilling Diverse Vision Foundation Models for Robot Learning. Theia is smaller but more powerful than off-the-shelf vision models in robotic tasks, and can generate features of SAM and DINOv2! Code, demo: https://theia.theaiinstitute.com/ Thank my co-authors! https://x.com/jsfiredrice/status/1831451779437068696/photo/1
๋ฏธ๋์ด
