Zhengxiong Luo | ByteDance Seed

About Me

I am currently a Staff Research Scientist at ByteDance Seed. Prior to this, I was a member of the Emu team at the Beijing Academy of Artificial Intelligence (BAAI) from June 2023 to February 2025.

I received my Ph.D. from the Institute of Automation, Chinese Academy of Sciences (CASIA), where I was advised by Prof. Tieniu Tan and worked closely with Prof. Liang Wang and Prof. Yan Huang. I obtained my Bachelor’s degree in Mechanical Engineering from Shanghai Jiao Tong University (SJTU) in 2018.

During my Ph.D., I gained extensive industry experience through internships, including a long-term engagement at Megvii Inc. (approximately 2.5 years), as well as a research internship at Alibaba DAMO Academy.

Research Interests

My current research focuses on unifying multimodal generation and understanding. My previous work has covered human pose estimation, low-level vision tasks, and video generation.

Selected Publications [Full List]

arXiv

Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation

Chao Liao, Liyang Liu, Xun Wang, Zhengxiong Luo, Xinyu Zhang, Wenliang Zhao, Jie Wu, Liang Li, Zhi Tian, Weilin Huang

arXiv preprint arXiv:2505.05472, 2025.

PDF

CVPR

CI-VID: A Coherent Interleaved Text-Video Dataset

Yiming Ju, Jijin Hu, Zhengxiong Luo, Haoge Deng, hanyu Zhao, Li Du, Chengwei Wu, Donglin Hao, Xinlong Wang, Tengfei Pan

arXiv preprint arXiv:2507.01938, 2025.

PDF Code

Nature

Emu3: Next-Token Prediction is All You Need

Xinlong Wang, Xiaosong Zhang, Zhengxiong Luo, Quan Sun, Yufeng Cui, Jinsheng Wang, Fan Zhang, Yueze Wang, Zhen Li, Qiying Yu, Yingli Zhao, Yulong Ao, Xuebin Min, Tao Li, Boya Wu, Bo Zhao, Bowen Zhang, Liangdong Wang, Guang Liu, Zheqi He, Xi Yang, Jingjing Liu, Yonghua Lin, Tiejun Huang, Zhongyuan Wang

arXiv preprint arXiv:2409.18869, 2024.

PDF Code Project Page

ICLR

Autoregressive video generation without vector quantization

Haoge Deng, Ting Pan, Haiwen Diao, Zhengxiong Luo, Yufeng Cui, Huchuan Lu, Shiguang Shan, Yonggang Qi, Xinlong Wang

arXiv preprint arXiv:2603.07102, 2026.

PDF

IJCV

End-to-End Alternating Optimization for Real-World Blind Super Resolution

Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan

International Journal of Computer Vision (IJCV), 2023, volume 131, pp. 3152-3169.

PDF Code

CVPR

VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation

Zhengxiong Luo, Dayou Chen, Yingya Zhang, Yan Huang, Liang Wang, Yujun Shen, Deli Zhao, Jinren Zhou, Tieniu Tan

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 10209-10218.

PDF

CVPR

Learning the Degradation Distribution for Deep Blind Super Resolution

Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 6063-6072.

PDF Code

CVPR

Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation

Zhengxiong Luo, Zhicheng Wang, Yan Huang, Liang Wang, Tieniu Tan, Erjin Zhou

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 13264-13273.

PDF

ICME

Efficient Human Pose Estimation by Learning Deeply Aggregated Representations

Zhengxiong Luo, Zhicheng Wang, Yuanhao Cai, Guan Wang, Yan Huang, Liang Wang, Tieniu Tan, Jian Sun

IEEE International Conference on Multimedia and Expo (ICME), 2021, pp. 1-6.

PDF

NeurIPS

Unfolding the Alternating Optimization for Blind Super Resolution

Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan

Advances in Neural Information Processing Systems (NeurIPS), 2020, volume 33, pp. 5632-5643.

PDF Code