Heung-Yeung Shum

LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

NoiseAR: AutoRegressing Initial Noise Prior for Diffusion Models

Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling