I am a second-year PhD student (2024 Fall-) in Computer Science at the University of Southern California, Institute for Creative Technologies, supervised by Prof. Mohammad Soleymani and Prof. Andrew (Wei-Wen) Feng.

I received my Master’s degree from University of Southern California, Institute for Creative Technologies. During my Master’s, I took Research Internships at Motorola Solutions and at TuSimple. Prior to that, I got my Bachelor degree from Shanghai Jiao Tong University.

My research interests mainly are in

1. 3D/4D Generation, 3D/4D Reconstruction.
2. Interactive Face/Head Generation, Reinforcement Learning for Visual Generation.
3. Video Understanding, including Group Activity Recognition, Multi-Object Tracking, etc.

Publications

GDPO-Listener: Expressive Interactive Head Generation via Auto-Regressive Flow Matching and Group reward-Decoupled Policy Optimization

Zhangyu Jin, Maksim Siniukov, Deuksin Kwon, Ashutosh Chaubey, Mohammad Soleymani

arXiv, 2026.

Paper Project

3DV 2026

SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priors

Zhangyu Jin, Andrew Feng

International Conference on 3D Vision (3DV), 2026

Paper Project Dataset

WACV 2026 Oral

PromptGAR: Flexible Promptive Group Activity Recognition

Zhangyu Jin, Andrew Feng, Ankur Chemburkar, Celso M. De Melo

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026 (Oral).

Paper Project

WACV 2026

Discrete Facial Encoding: A Framework for Data-driven Facial Display Discovery

Minh Tran, Maksim Siniukov, Zhangyu Jin, Mohammad Soleymani

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026.

Paper