auto-align

AI & ML interests

None defined yet.

Recent Activity

luxinyu  authored a paper about 9 hours ago

SoFA: Shielded On-the-fly Alignment via Priority Rule Following

luxinyu  authored a paper about 9 hours ago

Scalable Oversight for Superhuman AI via Recursive Self-Critiquing

luxinyu  authored a paper about 9 hours ago

On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation

View all activity

Team members 1