He Zhang

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

Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models

OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment

GroundingBooth: Grounding Text-to-Image Customization