OmniSafeAI

AI & ML interests

None defined yet.

Recent Activity

jijiaming  authored a paper 6 months ago

ProgressGym: Alignment with a Millennium of Moral Progress

XuehaiPan  authored a paper about 1 year ago

BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset

calico-1226  authored a paper about 1 year ago

Safe RLHF: Safe Reinforcement Learning from Human Feedback

View all activity

Team members 4