Luying Huang | Baidu VIS

About Me

I am currently a researcher of Baidu VIS. I received my B.S. & M.S. degree from Tongji University, School of Automotive Engineering.

Since 2024, I have been working at Department of Computer Vision Technology (VIS), Baidu Inc, working closely with Hang Zhou and Kaisiyuan Wang on both audio/video-driven high-fidelity and efficient human video synthesis techniques. Previously, I also had a pleasant work experience at Intelligent Driving Group (IDG), Baidu Inc, working on End-to-End(e2e) Autonomous Driving.

Research Interests

My research interests include both human-centric (e.g., Human Video Synthesis and Co-speech Gesture Generation) and object-centric (e.g., Object-Compositional Implicit Scene Generation) topics. Previously, I also pushed research in End-to-End Autonomous Driving.

News

[Jul. 2025] Our paper GestureHydra is accepted to ICCV 2025.
[Jun. 2023] We won 4th place at CVPR 2023 3D Occupancy Prediction Challenge.

Publications

ICCV

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† (*Equal Contribution, †Corresponding Author)

IEEE InternationalConference on Computer Vision (ICCV), 2025.

PDF Project Page BibTex

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

Yangyang Ding*, Luying Huang*, Jiachen Zhong (*Equal Contribution)

PDF Project Page BibTex