Yongkang Cheng

cyk1990422gmail.com

Hi! I'm currently a first-year PhD student in MLR Group, The MBZUAI. I'm working on Humanoid Interacting and Motion Generation, using multi-modal conditions such as speech, text scripts, keypoints and image. My works are priminaly focused on the avatars and humanoid robots. I received my M.E. from NWAFU, in 2024.6, and B.E. from NJAU, in 2021.6.

Prior to my PhD, I was a research scientist at Agibot X-Lab for Project LinkCraft, Astribot R&D Team for Robot Gesture Generation, and research intern Tencent AILab for motion generation.

Research interests

  • Interacting Humanoid Robot
  • Multi-Modal Generation for Motion
  • Robot Agent

Selected Publications

Header media
Aligning Foundation Model Priors and Diffusion-Based Hand Interactions for Occlusion-Resistant Two-Hand Reconstruction

Gaoge Han Yongkang Cheng Shaoli Huang† Zhe Chen Tongliang Liu

Computer Vision and Pattern Recognition, CVPR, 2026

Paper

Header media
ReBaR: Reference-Based Reasoning for Robust Pose Estimation from Monocular Images

Yongkang Cheng Mingjiang Liang Jifeng Ning Gaoge Han WeiLiu Shaoli Huang†

Pattern Recognition, 2026

Paper | Project Page |

Header media
HoloGest: Decoupled Diffusion and Motion Priors for Generating Holisticly Expressive Co-speech Gestures

Yongkang Cheng Shaoli Huang†

International Conference on 3D Vision, 3DV, 2025

Paper | Project Page | Product

Header media
DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech

Yongkang Cheng Shaoli Huang† Xuelin Chen Jifeng Ning Mingming Gong

The Association for the Advancement of Artificial Intelligence, AAAI, 2025

Paper | Project Page

Header media
ExpGest: Expressive Speaker Generation Using Diffusion Model and Hybrid Audio-Text Guidance

Yongkang Cheng Mingjiang Liang* Shaoli Huang† WeiLiu Jifeng Ning

International Conference on Multimedia and Expo, ICME, 2024

Paper | Code

Experience

Academic Services

  • Reviewer: CVPR, ECCV, ACMMM, WACV, ICME; IJCV, PR