← Search

Yasen Zhang

2 accepted papers

2026

RADAR: VQ-VAE Decoder of VAR is a Good Student for Restoring Against Degradation by Acceleration

CVPR 2026

Visual Autoregressive Modeling (VAR) has recently emerged as a powerful paradigm for image generation that surpasses diffusion models in efficiency and quality. However, accelerating attention computation in VAR is still challenging because attention patterns across scales exhibit strong and complex

Cited by 0SourceScholar
2018

DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning

NeurIPS 2018poster

The accurate exposure is the key of capturing high-quality photos in computational photography, especially for mobile phones that are limited by sizes of camera modules. Inspired by luminosity masks usually applied by professional photographers, in this paper, we develop a novel algorithm for learni…

Cited by 116SourcePDFScholar