← Search

Yuzhe Yao

2 accepted papers

2025

Manifold Constraint Reduces Exposure Bias in Accelerated Diffusion Sampling

ICLR 2025poster

Diffusion models have demonstrated significant potential for generating high-quality images, audio, and videos. However, their iterative inference process entails substantial computational costs, limiting practical applications. Recently, researchers have introduced accelerated sampling methods that…

Cited by 0SourcePDFScholar
2024

Timestep-Aware Correction for Quantized Diffusion Models

ECCV 2024poster

"Diffusion models have marked a significant breakthrough in the synthesis of semantically coherent images. However, their extensive noise estimation networks and the iterative generation process limit their wider application, particularly on resource-constrained platforms like mobile devices. Existi…

Cited by 4SourcePDFScholar