4 papers
Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness
Hangyeol Lee, Hyojeong Lee, Joo-Young Kim
Diffusion Transformers (DiTs) achieve superior image generation quality but suffer from quadratic computational complexity relative to token count. While various token reduction (T…
GranQ: Efficient Channel-wise Quantization via Vectorized Pre-Scaling for Zero-Shot QAT
Inpyo Hong, Youngwan Jo, Hyojeong Lee +3
Zero-shot quantization (ZSQ) enables neural network compression without original training data, making it a promising solution for restricted data access scenarios. To compensate f…
Advanced Knowledge Transfer: Refined Feature Distillation for Zero-Shot Quantization in Edge Computing
Inpyo Hong, Youngwan Jo, Hyojeong Lee +2
We introduce AKT (Advanced Knowledge Transfer), a novel method to enhance the training ability of low-bit quantized (Q) models in the field of zero-shot quantization (ZSQ). Existin…
MRNet: Multifaceted Resilient Networks for Medical Image-to-Image Translation
Hyojeong Lee, Youngwan Jo, Inpyo Hong +1
We propose a Multifaceted Resilient Network(MRNet), a novel architecture developed for medical image-to-image translation that outperforms state-of-the-art methods in MRI-to-CT and…