Hugging Face Trending Papers

CoCaRS: Correlation Calibration-Based Redundancy Suppression for Heterogeneous Knowledge Distillation

Read the original on Hugging Face Trending Papers →

Knowledge distillation (KD) enables a compact student model to learn from a powerful teacher and has become an effective paradigm for model compression. The emergence of diverse model architectures has extended KD from homogeneous to heterogeneous settings.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Jun 2

DASH: Dual-Branch Score Distillation for Guidance-Calibrated Compact Diffusion Models

arXiv:2606. 00798v1 Announce Type: cross Abstract: 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.

By Abdullah Al Shafi, Kazi Saeed Alam, Sk Imran Hossain, Engelbert Mephu Nguifo