Jason Kuen

6

Papers

81

Total Citations

Papers (6)

ImageFolder: Autoregressive Image Generation with Folded Tokens

SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis

Refer to Any Segmentation Mask Group With Vision-Language Prompts

DiffIP: Representation Fingerprints for Robust IP Protection of Diffusion Models

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying