arxiv:2605.29559
Xinyu Lu
luxinyu
ยท
AI & ML interests
None yet
Recent Activity
authored a paper about 2 hours ago
SoFA: Shielded On-the-fly Alignment via Priority Rule Following authored a paper about 2 hours ago
Scalable Oversight for Superhuman AI via Recursive Self-Critiquing authored a paper about 2 hours ago
On-Policy Self-Alignment with Fine-grained Knowledge Feedback for
Hallucination MitigationOrganizations
