Ph.D. Student, Johns Hopkins University
Baltimore, MD, U.S.
Email: guanlinwu0930 [at] gmail.com
[Curriculum Vitae (2025.3.29)]
My research interests includes Computer Vision, Multimodal Large Language Models and Multi-agent System.I'm an incoming Ph.D. student at Johns Hopkins University (JHU), advised by Prof. Hao Frank Yang. My recent research focus on visual representation in multimodal large language models (MLLMs) and multi-agent system. I received my Master's degree in Systems Engineering from JHU in 2025. Prior to that, I received my Bachelor's degree in Computer Science and Engineering from The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen) in 2024. During my undergraduate years, I'm fortunate to have been mentored by Prof. Lei Zhang at International Digital Economy Academy (IDEA).
Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset [pdf][code]
Yuhong Zhang*, Jing Lin*, Ailing Zeng*, Guanlin Wu*, Shunlin Lu*, Yurong Fu, Yuanhao Cai, Ruimao Zhang, Haoqian Wang, Lei Zhang†
Preprint
LLM agents can partially mimic human driving behaviors and decision values but better align with aggressive profiles [pdf]
Pu Wang, Guanlin Wu, Yang Zhao, Yichen Lin, Hao Frank Yang†
Transportation Research Part C: Emerging Technologies, 2026
Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study [pdf][code][website]
Guanlin Wu*, Boyan Su*, Yang Zhao, Pu Wang, Yichen Lin, Hao Frank Yang†
Advances in Neural Information Processing Systems (NeurIPS), 2025 (Spotlight, Top 3%)
Towards Optimal Mixture of Experts System for 3D Object Detection: A Game of Accuracy, Efficiency and Adaptivity [pdf][code]
Linshen Liu, Pu Wang, Guanlin Wu, Junyue Jiang, Hao Frank Yang†
IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), 2025
Towards Accurate and Efficient 3D Object Detection for Autonomous Driving: A Mixture of Experts Computing System on Edge [pdf][code]
Linshen Liu*, Boyan Su*, Junyue Jiang, Guanlin Wu, Cong Guo, Ceyu Xu, Hao Frank Yang†
International Conference on Computer Vision (ICCV), 2025
HumanMM: Global Human Motion Recovery from Multi-shot Videos [pdf][code][website]
Yuhong Zhang*, Guanlin Wu*, Ling-Hao Chen, Zhuokai Zhao, Jing Lin, Xiaoke Jiang, Jiamin Wu, Zhuoheng Li, Hao Frank Yang, Haoqian Wang†, Lei Zhang†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025