Shoufa Chen

I am a Senior Research Scientist at Meta, working on video generation and agents.

I received my Ph.D. in Computer Science from The University of Hong Kong (HKU), where I was advised by Prof. Ping Luo. Before that, I earned my bachelor's degree from Huazhong University of Science and Technology (HUST), under the supervision of Prof. Xinggang Wang.

During my Ph.D. studies, I interned at Apple (Cupertino), ByteDance (Beijing and Shanghai), Amazon (San Francisco), Meta (London), and Tencent (Shenzhen).

Email / Google Scholar / GitHub / X / LinkedIn

News

2026 Two papers, Tuna-2 and WavFlow, are accepted to NeurIPS 2026.
Jun 2026 We released TUA-Bench, a benchmark for general-purpose terminal-use agents.
2026 TUNA is accepted to CVPR 2026.

Papers

Selected first-author work. ^* denotes equal contribution.

Agents

Overview of the TUA-Bench benchmark pipeline

TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents

Shoufa Chen, Luyuan Wang, Xuan Yang, Zhiheng Liu, Yuren Cong, Yuanfeng Ji, Feiyan Zhou, Xiaohui Zhang, Fanny Yang, Belinda Zeng

arXiv 2026

Paper / Website

Overview of the MobileAgentBench architecture

MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents

Luyuan Wang, Yongyu Deng, Yiwei Zha, Guodong Mao, Qinmin Wang, Tianchen Min, Wei Chen, Shoufa Chen

AAAI Workshop 2025

Paper / Website

Image, Video & Audio Generation

WavFlow generates audio directly from waveform patches instead of a latent space

WavFlow: Audio Generation in Waveform Space

Feiyan Zhou, Luyuan Wang, Shoufa Chen, Zhe Wang, Zhiheng Liu, Yuren Cong, Xiaohui Zhang, Fanny Yang, Belinda Zeng

NeurIPS 2026

Paper / Code

PixelFlow: Pixel-Space Generative Models with Flow

Shoufa Chen, Chongjian Ge, Shilong Zhang, Peize Sun, Ping Luo

arXiv 2025

Paper / Code / Demo

Goku: Flow Based Video Generative Foundation Models

Shoufa Chen^*, Chongjian Ge^*, Yuqi Zhang, Yida Zhang, Fengda Zhu, Hao Yang, Hongxiang Hao, Wuhui, Zhichao Lai, Yifei Hu, Ting-Che Lin, Shilong Zhang, Fu Li, Chuan Li, Xing Wang, Yanghua Peng, Peize Sun, Ping Luo, Yi Jiang, Zehuan Yuan, Bingyue Peng, Xiaobing Liu

CVPR 2025

Paper / Code / Website

Controllable image generation results from ControlAR

ControlAR: Controllable Image Generation with Autoregressive Models

Zongming Li, Tianheng Cheng, Shoufa Chen, Peize Sun, Haocheng Shen, Longjin Ran, Xiaoxin Chen, Wenyu Liu, Xinggang Wang

ICLR 2025

Paper / Code

LlamaGen: Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Peize Sun, Yi Jiang, Shoufa Chen, Shilong Zhang, Bingyue Peng, Ping Luo, Zehuan Yuan

arXiv 2024

Paper / Code

GenTron: Diffusion Transformers for Image and Video Generation

Shoufa Chen^*, Mengmeng Xu^*, Jiawei Ren, Yuren Cong, Sen He, Yanping Xie, Animesh Sinha, Ping Luo, Tao Xiang, Juan-Manuel Perez-Rua

CVPR 2024

Paper / Website

FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing

Yuren Cong, Mengmeng Xu, Christian Simon, Shoufa Chen, Jiawei Ren, Yanping Xie, Juan-Manuel Perez-Rua, Bodo Rosenhahn, Tao Xiang, Sen He

ICLR 2024

Paper / Code / Website

Unified Multimodal Models

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Zhiheng Liu, Weiming Ren, Xiaoke Huang, Shoufa Chen, Tianhong Li, Mengzhao Chen, Yatai Ji, Sen He, Jonas Schult, Belinda Zeng, Tao Xiang, Wenhu Chen, Ping Luo, Luke Zettlemoyer, Yuren Cong

NeurIPS 2026

Paper / Website

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Zhiheng Liu, Weiming Ren, Haozhe Liu, Zijian Zhou, Shoufa Chen, Haonan Qiu, Xiaoke Huang, Zhaochong An, Fanny Yang, Aditya Patel, Viktar Atliha, Tony Ng, Xiao Han, Chuyan Zhu, Chenyang Zhang, Ding Liu, Juan-Manuel Perez-Rua, Sen He, Jürgen Schmidhuber, Wenhu Chen, Ping Luo, Wei Liu, Tao Xiang, Jonas Schult, Yuren Cong

CVPR 2026

Paper / arXiv / Website