website picture

Hanbo Zhang

Research Fellow @ National University of Singapore
Email: zhanghanbo163@outlook.com
Google Scholar| Linked In| GitHub
Previously:
Robotics Researcher @ ByteDance Research
PhD Candidate @ Xi'an Jiaotong University
Visiting PhD Student @ National University of Singapore


I am currently a Postdoctoral Research Fellow in National University of Singapore working with Prof. David Hsu. Previously, I spent around 2 years working as a robotics researcher in ByteDance Research, working closely with Tao Kong. Before that, I graduated as a PhD in Control Science and Engineering in Xi'an Jiaotong University, Xi’an, China, in 2022, under the supervision of Prof. Xuguang Lan.

We are recruiting interns working on human-robot interaction and uncertainty-aware planning for robotics! Drop me an email if you are interested.

Research Keywords: Long-horizon Interactive Manipulation; Human-Robot Interaction; Robot Grasping System



Recent Works

[Full Publication List]

† Corresponding Author, * Co-first Author

GR2 GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
Robotics Research Team, ByteDance Research, Tech. Report, 2024
ArXiv Website Video


TiO Towards Unified Interactive Visual Grounding in The Wild
ICRA 2024.
Jie Xu, Hanbo Zhang† , Qingyi Si, Yifeng Li, Xuguang Lan, Tao Kong
ArXiv Website Code


RoboFlamingo Vision-Language Foundation Models as Effective Robot Imitators
ICLR 2024.
Xinghang Li*, Minghuan Liu*, Hanbo Zhang, Cunjun Yu, Jie Xu, Hongtao Wu, Chilam Cheang, Ya Jing, Weinan Zhang, Huaping Liu, Hang Li, Tao Kong
ArXiv Website Code


InViG Invig: Benchmarking interactive visual grounding with 500k human-robot interactions
CVPRW 2024.
Hanbo Zhang*, Jie Xu*, Yuchen Mo, Tao Kong
ArXiv Website Code Data


Lynx What matters in training a gpt4-style language model with multimodal inputs?
NAACL 2024.
Ranks 11th of the most influential papers in NAACL 2024
Yan Zeng*, Hanbo Zhang*, Jiani Zheng, Jiangnan Xia, Guoqiang Wei, Yang Wei, Yuchen Zhang, Tao Kong
ArXiv Website


REGRAD REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter
RAL with ICRA presentation, 2022.
Hanbo Zhang*, Deyu Yang*, Han Wang*, Binglei Zhao, Xuguang Lan, Jishiyu Ding, Nanning Zheng
ArXiv Data


invigorate INVIGORATE: Interactive Visual Grounding and Grasping in Clutter
RSS 2021.
Hanbo Zhang*, Yunfan Lu*, Cunjun Yu, David Hsu, Xuguang Lan, Nanning Zheng.
ArXiv Code Demo


Mentorship

Site Bai Ph.D. Candidate Xinghang Li Ph.D. Candidate
Chengzhong Ma Ph.D. Candidate Shiguang Sun Ph.D. Candidate
Han Wang Ph.D. Candidate Jie Xu ByteDance, Beijing
Chenjie Yang ByteDance, Shanghai Deyu Yang SenseTime, Shanghai
Binglei Zhao JD, Beijing


Professional Activities

Journal Reviewer: IJRR, AURO, RAL, TPAMI, TASE, TNNLS, TSMC
Conference Reviewer: RSS, ICRA, IROS, AAMAS