Yiren Song

Personalized Vision via Visual In-Context Learning

MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation

Mitty: Diffusion-based Human-To-Robot Video Generation

Anti-Reference: Universal and Immediate Defense Against Reference-Based Generation

OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data

Image Watermarks are Removable using Controllable Regeneration from Clean Noise

GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains

WMAdapter: Adding WaterMark Control to Latent Diffusion Models

RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers

Personalized Vision via Visual In-Context Learning

WMAdapter: Adding WaterMark Control to Latent Diffusion Models

Anti-Reference: Universal and Immediate Defense Against Reference-Based Generation