Yilin Wang

11

Papers

166

Total Citations

Papers (11)

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

Dolfin: Diffusion Layout Transformers without Autoencoder

Bayesian Diffusion Models for 3D Shape Reconstruction

FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity

UniHuman: A Unified Model For Editing Human Images in the Wild

OmniStyle: Filtering High Quality Style Transfer Data at Scale

MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer

SigStyle: Signature Style Transfer via Personalized Text-to-Image Models

Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion

TokenCompose: Text-to-Image Diffusion with Token-level Supervision

Spatial-Temporal Forgery Trace based Forgery Image Identification