Yushi Hu

Yushi Hu is a Research Scientist at Meta, focusing on Next-Gen Multimodal Models within the Fundamental AI Research (FAIR) team. Previously, Yushi served as a Research Scientist Intern for the GenAI Llama team at Meta, and as a Research Intern at Tencent's AI Lab in Seattle, specializing in speech synthesis and self-supervised pretraining. Additionally, Yushi worked as a Student Researcher at Google on a Large Multimodal Model, and as a Research Assistant at the Toyota Technological Institute at Chicago (TTIC), where the focus was on speech self-supervised learning and automatic speech recognition. Yushi is pursuing a Doctor of Philosophy (PhD) degree at the University of Washington, expected to be completed in 2025.