Chendong Xiang(项晨东)

Biography

I am a third-year PhD at Tsinghua University, computer science and technology, TSAIL Group, advised by Prof. Jun Zhu. I'm interested in large-scale generative models, embodied AI, and machine learning systems.

Before that, I received my B.E. degree from the Department of Computer Science and Technology, Tsinghua University in July, 2024.

I had research experiences on diffusion models, Rectified Flow, and their applications in image generation, 3D generation and video generation; also with machine learning system, sparse attention.

Email: xcd24@mails.tsinghua.edu.cn · GitHub · Google Scholar

Research Highlight

• Efficient Sparse Attention
  • SpargeAttn: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
  • SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
• Video based World Model and Robot manipulation
  • Vidar: Embodied Video Diffusion Model for Generalist Manipulation
  • Vidarc: Low Latency Embodied Video Diffusion Model with Closed-loop Control
  • Motubrain: An Advanced World Action Model for Robot Control

Publications

• SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
  Jintao Zhang*, Kai Jiang*, Chendong Xiang*, Weiqi Feng, Yuezhou Hu, Haocheng Xi, Jianfei Chen, Jun Zhu
  (NeurIPS 2026)
• SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference
  Jintao Zhang*, Chendong Xiang*, Haofeng Huang*, Haocheng Xi, Jia Wei, Jun Zhu, Jianfei Chen
  (ICML2025) [code]
• Identifying and Solving Conditional Image Leakage in Image to-Video Generation
  Min Zhao*, Hongzhou Zhu*, Chendong Xiang, Kaiwen Zheng, Chongxuan Li, Jun Zhu
  (NeurIPs2024) [code] / [website]
• FeedFace: Efficient Inference-based Face Personalization via Diffusion Models
  Chendong Xiang, Armando Fortes, Khang Hui Chua, Hang Su, Jun Zhu
  International Conference on Learning Representations (ICLR2024)
  [code]
• CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model
  Zhengyi Wang, Yikai Wang, Yifei Chen, Chendong Xiang, Shuo Chen, Dajiang Yu, Chongxuan Li, Hang Su, Jun Zhu
  (ECCV2024) [code]

* indicates co-first authors.

Preprints

• Motubrain: An Advanced World Action Model for Robot Control
  Motubrain Team, Chendong Xiang, Fan Bao, Haitian Liu, Hengkai Tan, Hongzhe Bi, James Li, Jiabao Liu, Jingrui Pang, Kiro Jing, Louis Liu, Mengchen Cai, Rongxu Cui, Ruowen Zhao, Runqing Wang, Shuhe Huang, Yao Feng, Yinze Rong, Zeyuan Wang, Jun Zhu
  
• Geometry-Aware Rotary Position Embedding for Consistent Video World Model (ViewRope)
  Chendong Xiang*, Jiajun Liu*, Jintao Zhang*, Xiao Yang, Zhengwei Fang, Shizun Wang, Zijun Wang, Yingtian Zou, Hang Su, Jun Zhu
  
• Vidu S1: A Real-Time Interactive Video Generation Model
  Jintao Zhang, Kai Jiang, Jintao Chen, Xu Wang, Yang Luo, Yuji Wang, Dechuang Chen, Jungang Li, Chengyang Ye, Marco Chen, Hongzhou Zhu, Min Zhao, Yuxuan Jiang, Zhengkun Huang, Chendong Xiang, Kaiwen Zheng, Haoxu Wang, Xiaohang Wang, Qi Jia, Xin Chen, Yimin Chen, Youhe Jiang, Fangcheng Fu, Zhijie Deng, Fan Bao, Jianfei Chen, Jun Zhu
  
• Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
  Jintao Zhang, Kai Jiang, Jintao Chen, Xu Wang, Deyuan Liu, Jungang Li, Dechuang Chen, Ming Lin, Jingjiang Zhou, Haopeng Jin, Qi Jia, Xiaohang Wang, Yaole Wang, Zhanqiang Zhang, Ran Li, Zhengkun Huang, Shuyue Xiong, Yuji Wang, Zikun Dai, Hui He, Yang Luo, Mang Ning, Weiqi Feng, Chengyang Ye, Xinyue Lin, Min Zhao, Hongzhou Zhu, Hengkai Tan, Zeyuan Wang, Chendong Xiang, Kaiwen Zheng, Zhijie Deng, Fan Bao, Jianfei Chen, Jun Zhu
  
• Vidarc: Low Latency Embodied Video Diffusion Model with Closed-loop Control
  Yao Feng*, Chendong Xiang*, Xinyi Mao, Hengkai Tan, Zuyue Zhang, Shuhe Huang, Kaiwen Zheng, Haitian Liu, Hang Su, Jun Zhu
  
• Vidar: Embodied Video Diffusion Model for Generalist Manipulation
  Yao Feng, Hengkai Tan, Xinyi Mao, Chendong Xiang, Guodong Liu, Shuhe Huang, Hang Su, Jun Zhu
  
• Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models
  Fan Bao, Chendong Xiang*, Gang Yue*, Guande He*, Hongzhou Zhu*, Kaiwen Zheng*, Min Zhao*, Shilong Liu*, Yaole Wang*, Jun Zhu
  
• A Closer Look at Parameter-Efficient Tuning in Diffusion Models
  Chendong Xiang, Fan Bao, Chongxuan Li, Hang Su, Jun Zhu
  [code]

Competitions

• International Algorithm Case Competition(IACC), Champion, 2023.12
• Computer System Development Capability Competition, OS functional design, First Prize, 2022.8
• ACM-China International Parallel Computing Challenge（IPCC）, Third Prize(Fourth place), 2022.10
• Chinese Chemistry Olympiad（CChO）, Gold Medal, 2018

Honors & Awards

• Science and Technology Innovation Excellent Scholarship, Tsinghua University, 2022
• Excellent Volunteer Scholarship, Tsinghua University, 2022
• Literary and Arts Excellence Scholarship, Tsinghua University, 2021, 2020
• National Encouragement Scholarship, 2020

Services

Contributor

• huggingface/diffusers, the most widely-used library for diffusion models.
• allenai/OLMo, state-of-the-art open language models.