← Search

Jianwei Dr. Zhang

2 accepted papers

2026

Consistent Text-to-Image Generation via Scene De-Contextualization

ICLR 2026poster

Consistent text-to-image (T2I) generation seeks to produce identity-preserving images of the same subject across diverse scenes, yet it often fails due to a phenomenon called identity (ID) shift. Previous methods have tackled this issue, but typically rely on the unrealistic assumption of knowing al…

Cited by 0SourcecodeScholar
2025

Proxy Denoising for Source-Free Domain Adaptation

ICLR 2025oral

Source-Free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to an unlabeled target domain with no access to the source data. Inspired by the success of large Vision-Language (ViL) models in many applications, the latest research has validated ViL's benefit for SFDA by using their p…