Jun-Yan Zhu

7

Papers

154

Total Citations

Papers (7)

SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models

Multi-subject Open-set Personalization in Video Generation

Generating Multi-Image Synthetic Data for Text-to-Image Customization

Generating Physically Stable and Buildable Brick Structures from Text

Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization

Generative Photomontage

On the Content Bias in Fréchet Video Distance