I am a first-year Ph.D. student at the HKU Musketeers Foundation Institute of Data Science (HKU-IDS), as well as HKU-MMLab, The University of Hong Kong, supervised by Prof. Xihui Liu.

I received my B.Eng. Degree from the University of Electronic Science and Technology of China (UESTC) and MPhil Degree from The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), supervised by Prof. Xiaoguang Han. Before joining HKU-IDS, I’ve spent wonderful time with great minds and interesting friends at Shanghai AI Laboratory.

My current research interests lie in the Multimodal Large Language Models and 3D Vision and Robotics (Embodied AI). I’m open to potential collaborations, feel free to drop me an email if you are interested in.

🔥 News

2024.06: 🎉🎉 We realse a new task: 3D reasoning grounding and benchmark: ScanReason to examine the 3D understanding ability in the era of Foundation Model.
2024.06: The report of our follow-up work with the most-ever hierarchical grounded language annotations, MMScan, has been released.
2024.02: We will co-organize Autonomous Grand Challenge in CVPR 2024. Welcome to try the Multi-View 3D Visual Grounding track!
2024.02: 🎉🎉 Our EmbodiedScan is accepted by CVPR 2024!

📝 Publications

ECCV 2024

Empowering 3D Visual Grounding with Reasoning Capabilities

Arxiv preprint
Chenming Zhu, Tai Wang, Wenwei Zhang, Kai Chen, Xihui Liu†

MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations

Arxiv preprint
Ruiyuan Lyu*, Tai Wang*, Jingli Lin*, Shuai Yang*, Xiaohan Mao, Yilun Chen, Runsen Xu, Haifeng Huang, Chenming Zhu, Dahua Lin, Jiangmiao Pang†

CVPR 2024

EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024
Tai Wang*, Xiaohan Mao*, Chenming Zhu*, Runsen Xu, Ruiyuan Lyu, Peisen Li, Xiao Chen, Wenwei Zhang, Kai Chen, Tianfan Xue, Xihui Liu, Cewu Lu, Dahua Lin, Jiangmiao Pang†

📖 Projects

MMDetection3D: OpenMMLab next-generation platform for general 3D perception. (Github >5k stars 🔥)
C0RE MAINTAINER & DEVELOPER

MMDetection3D unifies the pipeline and modular design of mono3D, LiDAR-based,and multi-modality 3D object detection.
It supports state-of-the-art 3D object detectors of different modalities in multiple indoor and outdoor datasets.
It builds strong foundations,in a universal framework, for general 3D object detection.

🎖 Honors and Awards

2023.10 Runner-up of Waymo Camera-Only 3D Detection Challenge, CVPR 2022
2017-2018/2018-2019 Excellent Undergraduate Scholarship of UESTC
2018 Outstanding Student Award of School of Computer Science and Engineering, UESTC

💬 Academic Services

I served as a reviewer for CVPR, ICCV, ECCV, NeurIPS.

💻 Internships