๐คAbout Me
I am a PhD student at MBZUAI, advised by Prof. Tongliang Liu. Previously, I was a research assiatant at City University of Hong Kong, supervised by Prof. Kede Ma. Before this, I was a research intern at Tencent AI Lab, supervised by Dr. Shaoli Huang.
My research topic is AI, with a particular focus on Human Perception Evaluation, 3D Human Motion Generation and Hand Pose Estimation. Previously, I focused on high-level vision, e.g., Object Detection/Segmentation and Computer Vision in Agriculture.
๐ฃResearch Experience
ย ย ย ย

๐ฅ News
- 2025.07 ย ๐๐ Two papers are accepted by Pattern Recognition 2025.
- 2025.07 ย ๐ One paper is accepted by ICMR 2025.
- 2025.06 ย ๐ญ One paper is rejected by ICCV 2025.
- 2025.02 ย ๐ An invention patent application has been granted by the Chinese Patent Office.
- 2025.02 ย ๐ I have received a 2025 Fall PhD offer in Machine Learning from MBZUAI (CS Rankings 9th in AI globally).
- 2024.09 ย ๐๐ Two papers are accepted by WACV 2025 in Round 1 (acceptance rate 12%).
- 2024.09 ย I will start a Research Assistant at City University of Hong Kong, see you in Hong Kong.
- 2024.05 ย I will start a Research Intern at Tencent AI Lab, See you in Shenzhen.
- 2024.05 ย My graduation thesis received the highest blind review score in my department (98 91 90).
- 2024.04 ย ๐ One paper is accepted by Pattern Recognition (SCI Distinct 1 Top).
- 2024.03 ย HuTuMotion is accepted by VALSE 2024 Poster, see you in chongqing.
- 2023.12 ย ๐ One paper is accepted by AAAI 2024.
๐ Selected Publications
- Kernel-aware Dynamic Convolution for Dense Prediction
Gaoge Han, Mingjiang Liang, Jinglei Tang, yongkang cheng, Wei Liu, Shaoli Huang
Pattern Recognition (PR 2025)
- ReBaR: Reference-Based Reasoning for Robust Pose Estimation from Monocular Images
Yongkang Cheng, Mingjiang Liang, Jifeng Ning, Gaoge Han, Wei Liu, Shaoli Huang
Pattern Recognition (PR 2025)
- Inter-Diffusion Generation Model of Speakers and Listeners for Effective Communication
Jinhe Huang, Yongkang Cheng, Yuming Hang, Gaoge Han, Jinewei Li, Jing Zhang, Xingjian Gu
ACM International Conference on Multimedia Retrieval (ICMR 2025)
- ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model
Gaoge Han, Mingjiang Liang, Jinglei Tang,yongkang cheng, Wei Liu, Shaoli Huang
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)
- Conditional GAN for Enhancing Diffusion Models in Efficient and Authentic Global Gesture Generation from Audio
Yongkang Cheng, Mingjiang Liang, Shaoli Huang, Gaoge Han, Jifeng Ning, Wei Liu
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)
- SIAM: A Parameter-free, Spatial Intersection Attention Module
Gaoge Han, Shaoli Huang, Fang Zhao, Jinglei Tang
Pattern Recognition (PR 2024)
- ExpGest: Expressive Full-Body Gesture Generation Using Diffusion Model and Hybrid Audio-Text Guidance
Yongkang Cheng, Mingjiang liang, Shaoli Huang, Gaoge Han, Wei Liu, Jifeng Ning
IEEE International Conference on Multimedia & Expo (ICME 2024)
- HuTuMotion: Human-Tuned Latent Motion Diffusion Models with Minimal Feedback
Gaoge Han, Shaoli Huang, Mingming Gong, Jinglei Tang
AAAI Conference on Artificial Intelligence (AAAI 2024)
๐
Honors and Awards
- 2024.6 Northwest A&F University Outstanding Graduate Dissertation (8/127).
- 2024.5 Northwest A&F University Outstanding Graduate (1/127).
๐ Services
Conference Reviewers