AI RESEARCH
DASH: Dual-Branch Score Distillation for Guidance-Calibrated Compact Diffusion Models
arXiv CS.AI
•
ArXi:2606.00798v1 Announce Type: cross Parameter compression of class-conditional diffusion models reveals an underexplored limitation in output-level distillation: the unconditional score branch remains unsupervised, leaving the classifier-free guidance gap underdetermined in the student. This gap, amplified at every denoising step, admits degenerate solutions where both branches collapse toward identical predictions, rendering guidance ineffective despite low output-level