DailyPapers (@HuggingPapers)
2025-12-15 | โค๏ธ 301 | ๐ 52
Microsoft just dropped VITRA-VLA, a new Vision-Language-Action model for robotics on Hugging Face.
It learns dexterous manipulation from over 1 million real-life human hand activity videos. https://x.com/HuggingPapers/status/2000441055976595566/video/1
๐ ์๋ณธ ๋งํฌ
๋ฏธ๋์ด
