Ziyang Xie

I’m the Co-Founder & CTO of Braintrance, building a next-generation immersive media platform that brings 4D spatial content to everyone. Before Braintrance, I co-founded Manifolds-AI, a 3D native GenAI platform for e-commerce content creation.

Previously, I studied CS at UCLA (advised by Prof. Bolei Zhou). I received my Master’s degree (MSCS) from UIUC, where I worked closely with Prof. Yuxiong Wang and Prof. Shenlong Wang. I completed my undergraduate studies at Fudan University with Prof. Li Zhang.

My work spans 3D vision, simulation, generative models, and intelligent systems that interact with the physical world.

Thesis

Master Thesis: Build Realistic and Interactive 3D Scene Simulation from In-the-wild Videos, University of Illinois Urbana-Champaign, 2025.

News

Feb 27, 2025	One new paper accepted by CVPR 2025 .
Feb 6, 2025	One new paper accepted by TPAMI (IF 20.8) as Regular Paper.
May 5, 2024	This summer, I will be joining Prof. Bolei Zhou’s group at UCLA as a research intern.
Jan 16, 2024	One new paper accepted for ICLR 2024 Spotlight Presentation! 🎉
Oct 30, 2023	Glad to be invited to serve as a reviewer for CVPR 2024!

Projects

WorldGen - Generate Any 3D Scene in Seconds

WorldGen is a powerful AI model that creates interactive 3D scenes from text and image inputs in seconds. It supports instant 3D generation from text or image and 360° free exploration with loop closure.

Project Page Code 777

Publications

Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation

Ziyang Xie, Zhizheng Liu, Zhenghao Peng, Wayne Wu, and Bolei Zhou

CVPR, 2025

arXiv Project Page Bib

@article{xie2024vid2sim,
  title = {Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation},
  author = {Xie, Ziyang and Liu, Zhizheng and Peng, Zhenghao and Wu, Wayne and Zhou, Bolei},
  page = {https://metadriverse.github.io/vid2sim/},
  journal = {CVPR},
  year = {2025}
}

S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation

Yurui Chen, Junge Zhang, Ziyang Xie, Wenye Li, Feihu Zhang, and 2 more authors

TPAMI, 2025

arXiv Bib

@article{yurui2023snerf++,
  title = {S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation},
  author = {Chen, Yurui and Zhang, Junge and Xie, Ziyang and Li, Wenye and Zhang, Feihu and Lu, Jiachen and Zhang, Li},
  journal = {TPAMI},
  year = {2025}
}

Frozen transformers in language models are effective visual encoder layers

Ziqi Pang, Ziyang Xie*, Yunze Man*, and Yu-Xiong Wang

ICLR, 2024 | Spotlight*

arXiv Code Bib
@article{pang2023frozen, author = {Pang, Ziqi and Xie*, Ziyang and Man*, Yunze and Wang, Yu-Xiong}, journal = {ICLR}, year = {2024} }

MV-Map: Offboard HD-Map Generation with Multi-view Consistency

Ziyang Xie*, Ziqi Pang*, and Yu-Xiong Wang

ICCV, 2023

arXiv Code Bib

@article{ziyang2023mvmap,
  title = {MV-Map: Offboard HD-Map Generation with Multi-view Consistency},
  author = {Xie*, Ziyang and Pang*, Ziqi and Wang, Yu-Xiong},
  journal = {ICCV},
  year = {2023}
}

S-NeRF: Neural Radiance Fields for Street Views

Ziyang Xie*, Junge Zhang*, Wenye Li, Feihu Zhang, and Li Zhang

ICLR, 2023

Project Page Bib

@article{ziyang2023snerf,
  title = {S-NeRF: Neural Radiance Fields for Street Views},
  author = {Xie*, Ziyang and Zhang*, Junge and Li, Wenye and Zhang, Feihu and Zhang, Li},
  page = {https://ziyang-xie.github.io/s-nerf/},
  journal = {ICLR},
  year = {2023}
}

Experience

Braintrance
Cofounder & CTO
Dec. 2025 – Present

Manifolds-AI (极泛流形)
Tech-Founder & CTO
Sep. 2023 – Oct. 2025

SenseTime
Autonomous Driving Research Intern
Jan. 2022 – Jul. 2022

Education

University of California, Los Angeles
CS PhD Student
Sep. 2025 – Apr 2026

University of Illinois Urbana-Champaign
Master of Science in Computer Science (MSCS)
Aug. 2023 – May 2025

Fudan University
Bachelor of Science in Computer Science
Sep. 2019 – June 2023