Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models Paper • 2610.03665 • Published 7 days ago • 60
PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization Paper • 2608.30597 • Published Aug 31 • 27
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation Paper • 2609.08798 • Published about 1 month ago • 84