Tengyue Zhang

E-mail GitHub X-LANCE Lab

About Me

I’m a senior undergrad @ Shanghai Jiao Tong University (SJTU), with a major in the Zhiyuan Honors Program (Physics Track) and a minor in Computer Science. I plan to pursue a CS Ph.D. in XLance in Fall 2027. Now I am at a internship with OpenMOSS at Shanghai Innovation Institute (SII).

My research interests lie on

  • representation learning and multimodal generative modeling. Particularly, I am interested in audio-visual generation (T2I/T2V/I2V), speech understanding and generation (ASR/TTS), and world models.
  • Science4AI, especially combining physical insights with AI to improve neural networks and solve scientific problems.

Find detailed interests and experiences in my CV!

Publications

Jiatong Zhao*, Tengyue Zhang*, Yuhan Wang*, Fuyuan Wu, Junchi Yan. Co4ICF: Co-evolving Physics-Informed Surrogate and RL-based Pulse Optimizer for Inertial Confinement Fusion. Accepted at KDD 2026 (* Equal Contribution)

Projects

I am a core dev of MOSS-Image GitHub stars , which is an open-source 5B-parameter text-to-image model with text rendering and layout control.

Recent Posts

All Posts »