Shuhang Gu

Progressive Focused Transformer for Image Restoration

Advanced Pixel Diffusion Model with Guided Sparse Global Refinement

PixSGR, a novel Pixel diffusion framework with Sparse Global Refinement tailored for modeling the distribution of natural images directly in pixel space, is proposed, enabling non-local refinement beyond isolated patches without the quadratic cost of dense attention.

Beyond Token-Level Cross-Entropy: Fr\'echet Distributional Post-Training for Autoregressive Image Generation

FD-loss post-training is introduced, which adapts a pretrained discrete generator using representation-space Fr\'echet distance as the sole objective and reduces FID and $\mathrm{FD}_{r6}$ by 41.4% and 52.0% on average.