Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
Paper • 2602.07892 • Published
Guanglong Sun
long2333
·
AI & ML interests
None yet
Recent Activity
authored a paper about 5 hours ago
Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection authored a paper about 5 hours ago
MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning updated a model 1 day ago
long2333/MePoOrganizations
None yet
authored 2
papers about 5 hours ago