Luying Huang

Luying Huang

Researcher, Baidu AMU

I am currently a researcher at Baidu AMU. I received my B.S. and M.S. degrees from Tongji University, School of Automotive Engineering.

Since 2024, I have been working at Baidu VIS(now AMU), where I collaborate closely with Hang Zhou and Kaisiyuan Wang on high-fidelity and efficient human-centric video generation, with a particular focus on audio-driven and video-driven synthesis.

Previously, I worked at the Intelligent Driving Group (IDG), Baidu Inc., on end-to-end autonomous driving with Xiaoqing Ye and Yifu Zhang.

My research interests lie in human-centric generation, co-speech gesture synthesis, human video synthesis, and compositional video generation.

🔥 News

  • 2025.07: GestureHYDRA was accepted to ICCV 2025.
  • 2023.06: We won 4th place in the CVPR 2023 3D Occupancy Prediction Challenge.

📝 Publications

ICCV 2025
GestureHYDRA

GestureHYDRA: Semantic Co-speech Gesture Synthesis via Hybrid Modality Diffusion Transformer and Cascaded-Synchronized Retrieval-Augmented Generation

Quanwei Yang, Luying Huang, Kaisiyuan Wang†, Jiazhi Guan, Shengyi He, Fengluo Li, Hang Zhou, Lingyun Yu, Yingying Li, Haocheng Feng, Hongtao Xie†

[Project Page] [Code] [BibTeX]

  • ICCV 2025. Equal contribution. † Corresponding author.
arXiv 2026
ONE-SHOT

ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration

Fengyuan Yang, Luying Huang†, Jiazhi Guan*, Quanwei Yang, Dongwei Pan, Jianglin Fu, Haocheng Feng, Wei He, Kaisiyuan Wang, Hang Zhou*, Angela Yao

[Project Page] [BibTeX]

  • arXiv preprint. † Project leader. * Corresponding authors.
arXiv 2026
DISPLAY

DISPLAY: Directable Human-Object Interaction Video Generation via Sparse Motion Guidance and Multi-Task Auxiliary

Jiazhi Guan, Quanwei Yang, Luying Huang, Junhao Liang, Borong Liang, Haocheng Feng, Wei He, Kaisiyuan Wang†, Hang Zhou†, Jingdong Wang

[Project Page] [BibTeX]

  • arXiv preprint. Equal contribution. † Corresponding author.
arXiv 2026
InterDyad

InterDyad: Interactive Dyadic Speech-to-Video Generation by Querying Intermediate Visual Guidance

Dongwei Pan, Longwei Guo, Jiazhi Guan, Luying Huang, Yiding Li, Haojie Liu, Haocheng Feng, Wei He, Kaisiyuan Wang, Hang Zhou

[Project Page] [BibTeX]

  • arXiv preprint.
CVPR Challenge 2023
Multi-Scale Occ

Multi-Scale Occ: 4th Place Solution for CVPR 2023 3D Occupancy Prediction Challenge

Yangyang Ding, Luying Huang, Jiachen Zhong

[Challenge] [BibTeX]

  • CVPR 2023 3D Occupancy Prediction Challenge. Equal contribution.

🎖 Honors and Awards

  • 2025.07 ICCV 2025 paper acceptance for GestureHYDRA.
  • 2023.06 4th Place, CVPR 2023 3D Occupancy Prediction Challenge.

📖 Educations

  • Tongji University, School of Automotive Engineering, B.S. and M.S.

💼 Experiences

  • 2024. - Present, Researcher, Baidu AMU.
  • Previously, Intelligent Driving Group (IDG), Baidu Inc.

🛠 Selected Projects