Nanxuan Zhao

Learning an Image Editing Model without Image Editing Pairs

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning

Look&Learn: Where to Look? Bridging Perception and Grounding Gap in Vision-Language Models

Bézier Splatting for Fast and Differentiable Vector Graphics Rendering

On Mechanistic Circuits for Extractive Question-Answering

Understanding and Enhancing Context-Augmented Language Models Through Mechanistic Circuits

LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors

Mean-Shift Distillation for Diffusion Mode Seeking

Crafting Layered Designs from Pixels