Embodied AI / Humanoid Loco-Manipulation

Qingwei Ben

Hi! I’m Qingwei Ben (贲清炜), a second-year Ph.D. student at MMLab, The Chinese University of Hong Kong, supervised by Prof. Dahua Lin. My research focuses on Embodied AI, especially humanoid loco-manipulation and whole-body control. My research goal is to advance full-stack algorithms that bring robots into everyday homes. This summer, I will intern at NVIDIA GEAR Lab.

I am open to conversations around research collaboration, entrepreneurship, and adjacent ideas. Feel free to reach me by email at elgceben@gmail.com, or on WeChat at elgceben.

Embodied AI Humanoid Whole-body Control Loco-Manipulation World Action Model

News

Feb. 2026.

Sonic has been open-source

Feb. 2026.

Gallant, Viral and DoorMan have been accepted by CVPR 2026

Jan. 2026.

VBCom and OPFA have been accepted by ICRA 2026

June 2025.

HoST has been selected as RSS 2025 Best System Paper Finalist

Affiliations

2026

Research Intern

NVIDIA GEAR Lab

Working with Dr. Jim Fan, Prof. Yuke Zhu, and Dr. Zhengyi Luo.

2024-2028

Ph.D. Student

The Chinese University of Hong Kong / MMLab

Supervised by Prof. Dahua Lin.

2024-2026

Research Intern

Shanghai AI Lab / Intern Robotics

Worked with Dr. Jiangmiao Pang and Dr. Jingbo Wang.

2023

Visiting Student

UMass Amherst / MIT-IBM Watson AI Lab

Worked with Prof. Chuang Gan.

2023

Undergraduate Researcher

TEA Lab, IIIS, Tsinghua University

Worked with Prof. Huazhe Xu.

2020-2024

B.Sc. & B.Eng.

Weiyang College, Tsinghua University

Mathematics and Physics + Software Engineering.

Research

Representative Research

Humanoid loco-manipulation and navigation as the main research identity.

01 Gallant 2025 CVPR 2026

Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains

Qingwei Ben* / Botian Xu* / Kailin Li* / Feiyu Jia / Wentao Zhang / Jingping Wang / Jingbo Wang / Dahua Lin / Jiangmiao Pang

code pdf website

02 HOMIE 2025 RSS 2025

HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit

Qingwei Ben* / Feiyu Jia* / Jia Zeng / Junting Dong / Dahua Lin / Jiangmiao Pang

code pdf video website

Core Projects

Large-scale platforms and systems that shape the broader research stack.

01 SONIC 2025 In submission

SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control

Zhengyi Luo* / Ye Yuan* / Tingwu Wang* / Chenran Li* / Sirui Chen+ / Fernando Castañeda+ / Zi-Ang Cao+ / Jiefeng Li+ / David Minor+ / Qingwei Ben+ / Xingye Da+ / Runyu Ding / Cyrus Hogg / Lina Song / Edy Lim / Eugene Jeong / Tairan He / Haoru Xue / Wenli Xiao / Zi Wang / Simon Yuen / Jan Kautz / Yan Chang / Umar Iqbal / Linxi "Jim" Fan‡ / Yuke Zhu‡

code pdf website

02 GRUtopia 2024 Technical Report

GRUtopia: Dream General Robots in a City at Scale

Hanqing Wang* / Jiahe Chen* / Wensi Huang* / Qingwei Ben* / Tai Wang* / Boyu Mi* / Tao Huang / Siheng Zhao / Yilun Chen / Sizhe Yang / Peizhou Cao / Wenye Yu / Zichao Ye / Jialun Li / Junfeng Long / Zirui Wang / Huiling Wang / Ying Zhao / Zhongying Tu / Yu Qiao / Dahua Lin / Jiangmiao Pang

code pdf video

Others

Selected collaborations across tactile simulation, teleoperation, policy learning, and control.

01 TAG 2026 In submission

Feel Robot Feels: Tactile Feedback Array Glove for Dexterous Manipulation

Feiyu Jia* / Xiaojie Niu* / Sizhe Yang* / Qingwei Ben / Tao Huang / Feng Zhao / Jingbo Wang / Jiangmiao Pang

pdf website

02 OPFA 2026 ICRA 2026

One-Policy-Fits-All: Geometry-Aware Action Latents for Cross-Embodiment Manipulation

Juncheng Mu* / Sizhe Yang* / Hojin Bae* / Feiyu Jia / Qingwei Ben / Boyi Li / Huazhe Xu / Jiangmiao Pang

pdf website

03 DoorMan 2025 CVPR 2026

Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer

Haoru Xue* / Tairan He* / Zi Wang* / Qingwei Ben / Wenli Xiao / Zhengyi Luo / Xingye Da / Fernando Castañeda / Guanya Shi / Shankar Sastry / Linxi "Jim" Fan / Yuke Zhu

pdf website

04 VIRAL 2025 CVPR 2026

VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation

Tairan He* / Zi Wang* / Haoru Xue* / Qingwei Ben* / Zhengyi Luo / Wenli Xiao / Ye Yuan / Xingye Da / Fernando Castañeda / Shankar Sastry / Changliu Liu / Guanya Shi / Linxi Fan / Yuke Zhu

pdf website

05 BeamDojo 2025 RSS 2025

BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds

Huayi Wang / Zirui Wang / Junli Ren / Qingwei Ben / Tao Huang / Weinan Zhang / Jiangmiao Pang

pdf video website

06 HoST 2025 RSS 2025 Best System Paper Finalist

Learning Humanoid Standing-up Control across Diverse Postures

Tao Huang / Junli Ren / Huayi Wang / Zirui Wang / Qingwei Ben / Muning Wen / Xiao Chen / Jianan Li / Jiangmiao Pang

code pdf video website

07 VB-Com 2025 ICRA 2026

VB-Com: Learning Vision-Blind Composite Humanoid Locomotion Against Deficient Perception

Junli Ren / Tao Huang / Huayi Wang / Zirui Wang / Qingwei Ben / Jiangmiao Pang / Ping Luo

pdf video website

08 RoboDuet 2024 RA-L, ICRA 2024 Mobile-Manipulation Workshop

RoboDuet: A Framework Affording Mobile-Manipulation and Cross-Embodiment

Guoping Pan* / Qingwei Ben* / Zhecheng Yuan / Guangqi Jiang / Yandong Ji / Shoujie Li / Jiangmiao Pang / Houde Liu / Huazhe Xu

code pdf video website

09 DiffTactile 2024 ICLR 2024; RSS 2024 Noosphere Workshop Best Paper

DiffTactile: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation

Zilin Si* / Gu Zhang* / Qingwei Ben* / Branden Romero / Zhou Xian / Chao Liu / Chuang Gan

code pdf video website