SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Safe Reinforcement Learning
๐ ์ฐ๊ตฌ ๊ฐ์
Confidence Calibration์ ๋ชจ๋ธ์ด ์์ธกํ ํ๋ฅ ์ด ์ค์ ์ ๋ต์ผ ๊ฐ๋ฅ์ฑ๊ณผ ์ผ๋ง๋ ์ผ์นํ๋์ง๋ฅผ ๋ํ๋ด๋ ๊ฐ๋ ์ด๋ค.
This post is licensed under CC BY 4.0 by the author.