Yuxin Wen

Yuxin Wen

Senior Researcher

Tencent Hunyuan

Biography

I am a Senior Researcher on the Tencent Hunyuan team, where my current work focuses on multimodal alignment and motion generation.

Previously, I earned my Ph.D. in 2022 from the Gorilla Lab at South China University of Technology (SCUT), advised by Prof. Kui Jia.

My research interests lie in computer vision, computer graphics, and machine learning, with a recent focus on multimodal alignment and motion generation.

We are seeking motivated research interns on multimodal alignment and motion generation at Tencent Hunyuan in Shenzhen. If interested, please send your CV to rexwen@tencent.com.

Interests

  • Multimodal Learning
  • Motion Generation
  • Generative Models
  • 3D Vision

Education

  • PhD in information and Communication Engineering, 2017-2022

    South China University of Technology

  • BSc in Department of Information Engineering (Elite Class), 2013-2017

    South China University of Technology

Experience

 
 
 
 
 

Senior Researcher

Tencent

Oct 2022 – Present Shenzhen
Core contributor to research on multimodal alignment and motion generation at Tencent Hunyuan. Lead author of HY-Motion 1.0 — the first billion-parameter text-to-motion foundation model, open-sourced. Earlier at Tencent AI Lab: built production-grade lip-sync, facial-expression, and upper-body motion driving systems for flagship games at Tencent.
 
 
 
 
 

Research Intern / Student Researcher

DexForce

Nov 2021 – Sep 2022 Shenzhen
Serves as an algorithm engineer for industrial defect detection.
 
 
 
 
 

Research Intern

Alibaba DAMO Academy

Jun 2021 – Oct 2021 Shenzhen
Serves for DAMO Academy Research Internship program, under the supervision by Prof. Lei Zhang.
 
 
 
 
 

Research Assistant

University of Macau

Sep 2019 – Jan 2020 Macau
Serves for the FDCT Funded project with the State Key Laboratory of Internet of Things for Smart City.