ROSS: Relearning from Self-Generated Rollouts through Selective Supervision Paper • 2609.35954 • Published 3 days ago • 32
Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation Paper • 2609.02998 • Published 29 days ago • 17
D^3-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation Paper • 2608.24987 • Published Aug 25 • 28