About Me
Hi, I am a student at Tsinghua University, where I am supervised by Prof. Xiu Li. I received my B.Eng. Degree from Sun Yat-sen University in 2023, supervised by Prof. Guanbin Li. My research lies in Multi-modal Learning (Parameter-Efficient Transfer Learning) and Generative Models (Human-centric). I have broad interests and am always open to explore new and meaningful topics.
Interests
- Multi-modal Learning (Parameter-Efficient Transfer Learning: Vision & Language)
- Generative Models (Human-centric: 3D Motion & Video)
News
- [Jun. 2024] Two workshop paper are accepted to ICML 2024.
- [Jun. 2024] Our solution won 3rd place in the OVD challenge at CVPR 2024.
- [Dec. 2023] One paper is accepted to ICASSP 2024.
- [Dec. 2023] One paper is accepted to AAAI 2024.
- [Jul. 2023] One paper is accepted to ICCV 2023.
Researchs
Adaptation of Vision Language Models
- Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation
Zunnan Xu, Zhihong Chen, Yong Zhang, Yibing Song, Xiang Wan and Guanbin Li
ICCV 2023
[PDF] [PROJECT]
- Enhancing Fine-grained Multi-modal Alignment via Adapters: A Parameter-Efficient Training Framework for Referring Image Segmentation
Zunnan Xu, Jiaqi Huang, Ting Liu, Yong Liu, Haonan Han, Kehong Yuan, Xiu Li
WANT@ICML 2024
[PDF] [PROJECT]
Human Motion Generative Models
- MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models
Zunnan Xu, Yukang Lin, Haonan Han, Sicheng Yang, Ronghui Li, Yachao Zhang and Xiu Li
Arxiv 2024
[PDF] [PROJECT]
- Chain of Generation: Multi-Modal Gesture Synthesis via Cascaded Conditional Control
Zunnan Xu, Yachao Zhang, Sicheng Yang, Ronghui Li and Xiu Li
AAAI 2024
[PDF] [PROJECT]
- Freetalker: Controllable Speech And Text-Driven Gesture Generation Based On Diffusion Models For Enhanced Speaker Naturalness
Sicheng Yang, Zunnan Xu, Haiwei Xue, Yongkang Cheng, Shaoli Huang, Mingming Gong and Zhiyong Wu
ICASSP 2024
[PDF] [PROJECT]
Human Video Generative Models
- Alignment is All You Need: A Training-free Augmentation Strategy for Pose-guided Video Generation
Xiaoyu Jin, Zunnan Xu, Mingwen Ou, Wenming Yang
CVG@ICML 2024 (oral)
[PDF] [PROJECT]
3D Asset Generation
- REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment
Haonan Han, Rui Yang, Huan Liao, Jiankai Xing, Zunnan Xu, Xiaoming Yu, Junwei Zha, Xiu Li, Wanhua Li
Arxiv 2024
[PDF] [PROJECT]
- Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors
Yukang Lin, Haonan Han, Chaoqun Gong, Zunnan Xu, Yachao Zhang and Xiu Li
ACMMM 2024
[PDF] [PROJECT]
Honors & Awards
- China National Scholarship (Top 1%), Ministry of Education of PRC
- Tencent Rhino-Bird Research Elite Program (one of 51 students selected globally), Tencent
- Outstanding Graduate (Top 5%), Sun Yat-sen University
- Golden Prize in International Genetically Engineered Machine competition (iGEM), MIT
Service
- Reviewer: ICLR, NeurlPS, ACMMM, Applied Intelligence
Powered by Jekyll and Minimal Light theme.