Luxin Zhang

Member of Technical Staff, Stealth Video AI Startup
ex-Senior Research Engineer, Meta MSL

I am a Member of Technical Staff at a stealth AI startup. Previously, I was a Senior Research Engineer at Meta Superintelligence Labs (MSL), focusing on the research and development of media foundation models (Movie Gen) and Llama 4 omni model (multimodal generation). I received my M.S. in Computer Vision from Carnegie Mellon University, and B.S. in Computer Science from Peking University.

/ / CV / Email: luxinz[at]alumni.cmu.edu

Research Highlight

Meta Movie Gen: the most advanced media foundation models.

Publications

The Llama 4 Herd: The Beginning of A New Era of Natively Multimodal AI Innovation
Core Contributor, Multimodal Generation.
Meta Technical Report, 2025
[Blog]

Movie Gen: A Cast of Media Foundation Models
Core Contributor, The Movie Gen Team.
Meta Technical Report, 2024
[PDF] [Blog] [Video] [Bench]

MoCha: Towards Movie-Grade Talking Character Generation
Cong Wei, Bo Sun, Haoyu Ma, Ji Hou, Felix Juefei-Xu, Zecheng He, Xiaoliang Dai, Luxin Zhang, Kunpeng Li, Tingbo Hou, Animesh Sinha, Peter Vajda, Wenhu Chen
NeurIPS 2025
[PDF] [Project]

Animated Stickers: Bringing Stickers to Life with Video Diffusion
David Yan, Winnie Zhang, Luxin Zhang, Anmol Kalia, Dingkang Wang, Ankit Ramchandani, Miao Liu, Albert Pumarola, Edgar Schoenfeld, Elliot Blanchard, Krishna Narni, Yaqiao Luo, Lawrence Chen, Guan Pang, Ali Thabet, Peter Vajda, Amy Bearman, Licheng Yu
arXiv Preprint 2024
[PDF]

AVID: Any-Length Video Inpainting with Diffusion Model
Zhixing Zhang, Bichen Wu, Xiaoyan Wang, Yaqiao Luo, Luxin Zhang, Yinan Zhao, Peter Vajda, Dimitris Metaxas, Licheng Yu
CVPR 2024
[PDF] [Project] [Code]

Cloth Region Segmentation for Robust Grasp Selection
Jianing Qian, Thomas Weng, Luxin Zhang, Brian Okorn, David Held
IROS 2020
[PDF]

Atari-head: Atari Human Eye-Tracking and Demonstration Dataset
Ruohan Zhang, Calen Walshe, Zhuode Liu, Lin Guan, Karl Muller, Jake Whritner, Luxin Zhang, Mary Hayhoe, Dana Ballard
AAAI 2020
[PDF]

Modelling complex perception-action choices
Ruohan Zhang, Jake Whritner, Zhuode Liu, Luxin Zhang, Karl Muller, Mary Hayhoe, Dana Ballard
Journal of Vision 2018
[Link]

AGIL: Learning Attention from Human for Visuomotor Tasks
Ruohan Zhang, Zhuode Liu, Luxin Zhang, Jake A Whritner, Karl S Muller, Mary M Hayhoe, Dana H Ballard
ECCV 2018
[PDF]

Learning Attention Model from Human for Visuomotor Tasks
Luxin Zhang, Ruohan Zhang, Zhuode Liu, Mary Hayhoe, Dana Ballard
AAAI 2018
[PDF] [Video]

Visual Attention Guided Deep Imitation Learning
Ruohan Zhang, Zhuode Liu, Luxin Zhang, Karl S Muller Mary M Hayhoe, Dana H Ballard
spotlight paper, NIPS 2017 Cognitively Informed Artificial Intelligence Workshop
[PDF]

Experience

Jun. 2025 - present
Video AI Startup
Member of Technical Staff

Feb. 2023 - Jun. 2025
Meta, Super Intelligence Lab
Senior Research Engineer

Mar. 2020 - Feb. 2023
Meta, Reality Lab
Research Engineer

May. 2019 - Aug. 2019
Facebook
Research Engineer Intern

Feb. 2019 - Dec. 2019
The Robots Perceiving and Doing (RPAD) Lab, Carnegie Mellon University
Research Assistant to Professor David Held

Sep. 2017 - Jan. 2018
Big Data Mining Group, Microsoft Research Asia
Research Intern
Supervised by Dr. Borje Karlsson

Jul. 2017 - Sep. 2017
Vision, Cognition, and Action VR Lab, The University of Texas at Austin
Research Assistant to Professor Dana Ballard.

Sep. 2016 - Sep. 2017
Spatial and Temporal Restoration, Understanding and Compression Team (STRUCT), Peking University
Research Assistant to Professor Jiaying Liu