Chun-Hsiao Yeh

Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs

arXiv 2025

Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition

arXiv 2024

Magic-Me: Identity-Specific Video Customized Diffusion

arXiv 2024

Meta-Personalizing Vision-Language Models to Find Named Instances in Video

meta-personalizing-vision-language-models-to

Ta-Ying Cheng

Yi Ma

Yubei Chen

Andrew Markham

Bryan Russell

Chenyu Wang

Chuan-En Lin

Daquan Zhou

Fabian Caba Heilbron

H. T. Kung