P$^2$-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors Paper • 2611.03953 • Published 11 days ago • 70 • 8
P^2-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors Paper • 2611.03953 • Published 11 days ago • 70