I’m currently a master’s student at National University of Singapore majoring in Artificial Intelligence. Previously, I got my Bachelor’s degree from Shanghai Jiao Tong University, majoring in Computer Science and Technology (IEEE Pilot Class). Currently, I am an AI Scientist Intern at MiroMind AI, supervised by Dr. Bin Wang. I was fortunate to work under the supervision of Prof. Cewu Lu and Prof. Lixin Yang. My research interests include computer vision, multi-modal models and agentic frameworks.
🔥 News
- 2025.9: I will work as an AI Scientist Intern at MiroMind AI focusing on LLM agent frameworks.
- 2025.7: POEM-v2 has been accepted as a generalizable multi-view hand mesh reconstruction model.
- 2024.6: I will work as an intern in the AI department of bilibili this summer.
- 2023.12: One paper FAVOR was accepted by AAAI 2024
- 2023.07: I have spent wonderful two weeks attending the summer course IDS2301 at HKU-IDS.
- 2023.03: 🎉🎉 I joined MVIG and began exploring the field of Computer Vision.
📝 Publications
MiroFlow: Towards High-Performance, Robust, and Open-Source Reproducible Agent Framework for General Research Tasks
Shiqian Su, Sen Xing, Xuan Dong, Muyan Zhong, Bin Wang, Xizhou Zhu, Yuntao Chen, Wenhai Wang, Yue Deng, Pengxiang Zhu, Ziyuan Liu, Tiantong Li, Jiaheng Yu, Zhe Chen, Lidong Bing, Jifeng Dai
Knowing Thyself: Ego-Grounding for Personalized Question-Answering in Egocentric Videos
CVPR 2026
Junbin Xiao*, Shenglang Zhang*, Pengxiang Zhu, Angela Yao
Multi-view Hand Reconstruction with a Point-Embedded Transformer
Lixin Yang, Licheng Zhong, Pengxiang Zhu, Xinyu Zhan, Junxiao Kong, Jian Xu, Cewu Lu
POEM is a generalizable multi-view hand mesh reconstruction model which embeds a static basis point within the multi-view stereo space. To infer accurate 3D hand mesh from multi-view images, POEM introduce a point-embedded transformer decoder. By employing a combination of five large-scale multi-view datasets and sufficient data augmentation, POEM demonstrates superior generalization ability in real-world applications.
FAVOR: Full-body AR-driven Virtual Object Rearrangement Guided by Textual Instructions
AAAI 2024 | Paper
Kailin Li*, Lixin Yang*, Zenan Lin, Jian Xu, Xinyu Zhan, Yifei Zhao, Pengxiang Zhu, Wenxiong Kang, Kejian Wu, Cewu Lu
FAVOR is a novel dataset for Full-body AR-driven Virtual Object Rearrangement that uniquely employs motion capture systems and VR. A pipeline for producing digital human rearrangement motion sequences is also presented.
📇 Experiences
Machine Vision and Intelligence Group
Undergraduate Research Intern, 2023.3 - (now)
Advisor: Lixin Yang, Cewu Lu
🎖 Honors and Awards
- 2024 Academic Excellence Scholarship of SJTU (top 30%)
- 2023 Academic Excellence Scholarship of SJTU (top 10%)
- 2022 Academic Excellence Scholarship of SJTU (top 10%)
- 2022.3 Finalist of Mathematical Contest of Modeling (top 5%)
📖 Educations
- 2025.08 - Present, National University of Singapore, Singapore.
- 2021.09 - 2025.06, Shanghai Jiao Tong University, Shanghai, China.
- 2018.09 - 2021.06, Shanghai High School, Shanghai, China (Outstanding Graduate).