← Search

Chengyu Xie

2 accepted papers

2026

Jointly Conditioned Diffusion Model for Multi-View Pose-Guided Person Image Synthesis

ICASSP 2026poster

Pose-guided human image generation is limited by incomplete textures from single reference views and the absence of explicit cross-view interaction. We present jointly conditioned diffusion model (JCDM), a jointly conditioned diffusion framework that exploits multi-view priors. The appearance prior…

Cited by 0SourcePDFScholar
2026

Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons

ICML 2026poster

Multilingual safety remains significantly imbalanced, leaving non-high-resource (NHR) languages vulnerable compared to robust high-resource (HR) ones. Moreover, the neural mechanisms driving safety alignment remain unclear despite observed cross-lingual representation transfer.In this paper, we find…

Cited by 0SourceScholar