Siheng Zhao

I am a second-year CS Ph.D. Student at the University of Southern California, advised by Prof. Yue Wang. My research is supported by the Amazon PhD Fellowship. I received my Bachelor's degree with highest honors from the School of Artificial Intelligence at Nanjing University, under the supervision of Prof. Zhihua Zhou.

Currently, I am a Research Scientist Intern at NVIDIA GEAR (Generalist Embodied Agent Research), working with Prof. Yuke Zhu. I was a Member of Technical Staff Intern at Amazon FAR (Frontier AI & Robotics), working closely with Prof. Guanya Shi, Prof. C. Karen Liu, Dr. Rocky Duan, and Prof. Pieter Abbeel.

Previously, I had the privilege of working with Prof. Tao Yu (HKU), Prof. Lin Shao (NUS), and Dr. Jiangmiao Pang (Shanghai AI Lab).

Email  /  Google Scholar  /  Github  /  Twitter

profile photo
News
  • [Aug, 2026] Joined NVIDIA GEAR as a Research Scientist Intern!
  • [July, 2026] ResMimic is accepted by RSS 2026 WCBM Workshop.
  • [Jan, 2026] TWIST2 is accepted by ICRA 2026 as Oral.
  • [Jan, 2026] D-REX is accepted by ICLR 2026.
  • [Oct, 2025] RoboVerse wins Best Paper Award at IROS Workshop.
  • [Sep, 2025] I'm honored and grateful to receive the Amazon ML PhD Fellowship!
  • [Aug, 2025] RoLA is accepted by CoRL 2025 and ICCV 2025 gDT-IV Workshop as Oral.
  • [July, 2025] UH-1 is accepted by Humanoids 2025 as Oral.
  • [May, 2025] Joined Amazon Frontier AI & Robotics as a Member of Technical Staff Intern!
  • [Apr, 2025] RoboVerse is accepted by RSS 2025 as Oral.
  • [Sep, 2024] OSWorld is accepted by NeurIPS 2024.
  • [Sep, 2024] TieBot is accepted by CoRL 2024 as Oral.
  • [Jan, 2024] Text2Reward and Lemur are accepted by ICLR 2024 as Spotlight.
  • [Dec, 2023] Awarded SenseTime Scholarship (30 undergraduates in the field of AI in China).
  • [Dec, 2023] Awarded Nanjing University Top-Grade Scholarship (highest honor in Nanjing University).
  • [July, 2023] ClothesNet is accepted by ICCV 2023.
  • [June, 2023] DiffClothAI is accepted by IROS 2023 as Oral.
Research

Current topics:

  • Humanoid whole-body control and loco-manipulation.
  • Scaling up robot learning via scalable data generation.

Previous topics:

  • Differentiable simulation and manipulation of deformable objects.
  • Computer use agents.

Selected Publications

* denotes equal contribution. For the full publication list, please refer to my Google Scholar .

LadderMan: Learning Humanoid Perceptive Ladder Climbing
Siheng Zhao, Yuanhang Zhang, Ziqi Lu, Pieter Abbeel, Rocky Duan,
Koushil Sreenath, Yue Wang, C. Karen Liu†, Guanya Shi†
arXiv 2026
[arxiv] [project]

ResMimic: From General Motion Tracking to Humanoid Whole-Body Loco-Manipulation via Residual Learning
Siheng Zhao, Yanjie Ze, Yue Wang, C. Karen Liu†, Pieter Abbeel†,
Guanya Shi†, Rocky Duan†
RSS 2026 WCBM Workshop
[arxiv] [project]

TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System
Yanjie Ze, Siheng Zhao, Weizhuo Wang, Angjoo Kanazawa†, Rocky Duan†, Pieter Abbeel†, Guanya Shi†, Jiajun Wu†, C. Karen Liu†
ICRA 2026, Oral
[arxiv] [project]

Robot Learning from Any Images
Siheng Zhao*, Jiageng Mao*, Wei Chow, Zeyu Shangguan, Tianheng Shi, Rong Xue, Yuxi Zheng, Yijia Weng, Yang You, Daniel Seita, Leonidas Guibas, Sergey Zakharov, Vitor Guizilini, Yue Wang
CoRL 2025
ICCV 2025 gDT-IV Workshop, Oral
[arxiv] [project]

Universal Humanoid Robot Pose Learning from Internet Human Videos
Siheng Zhao*, Jiageng Mao*, Siqi Song*, Tianheng Shi, Junjie Ye, Mingtong Zhang, Haoran Geng, Jitendra Malik, Vitor Guizilini, Yue Wang
Humanoids 2025, Oral
[arxiv] [project] [dataset🤗]

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh Jing Hua, Zhoujun Cheng ... Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, Tao Yu
NeurIPS 2024, followed and used by OpenAI & Anthropic
[arxiv] [project]

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
Siheng Zhao*, Tianbao Xie*, Chen Henry Wu, Yitao Liu, Qian Luo, Victor Zhong, Yanchao Yang, Tao Yu
ICLR 2024, Spotlight
[arxiv] [project]

profile photo DiffClothAI: Differentiable Cloth Simulation with Intersection-free Frictional Contact and Differentiable Two-Way Coupling with Articulated Rigid Bodies
Xinyuan Yu*, Siheng Zhao*, Siyuan Luo, Gang Yang, Lin Shao
IROS 2023, Oral
[paper] [project]

Education
USC logo University of Southern California
Ph.D. in Computer Science (2024 - )
Advisor: Prof. Yue Wang
NJU logo Nanjing University
B.Eng. in Artificial Intelligence (2020 - 2024)
Ranking: 1/99, Advisor: Prof. Zhihua Zhou
NUS logo National University of Singapore
Exchange in Computer Science (2023)
Advisor: Prof. Lin Shao
Work Experience
AILAB logo Nvidia, Generalist Embodied Agent Research (GEAR)
Research Scientist Intern (2026 - 2027)
Manager: Prof. Yuke Zhu
AILAB logo Amazon, Frontier AI & Robotics (FAR)
Member of Technical Staff Intern (2025 - 2026)
Manager: Dr. Rocky Duan, Prof. Pieter Abbeel
AILAB logo Shanghai AI Lab, Intern Robotics
Research Intern (2024)
Manager: Dr. Jiangmiao Pang
HKU logo The University of Hong Kong, XLang Lab
Research Intern (2023 - 2024)
Advisor: Prof. Tao Yu
Services
  • Conference Reviewer:
    • AI & ML: NeurIPS' 25/24, ICLR' 26/25
    • Computer Vision: CVPR' 26/25, ICCV' 25, ECCV' 26/24, 3DV' 26, WACV' 26
    • Robotics: CoRL' 26/25, ICRA' 26/24, IROS' 26/25
  • Journal Reviewer:
    • IEEE Robotics and Automation Letter (RA-L)' 26/25
  • Teaching:
    • CSCI 566 Deep Learning and Its Application, 2025 Fall
Selected Honors & Awards
  • Best Paper Award at IROS Workshop, 2025
  • Amazon ML PhD Fellowship, 2025
  • University of Southern California PhD Fellowship, 2024
  • SenseTime Scholarship, 2023, awarded to 30 undergraduates in the field of AI in China
  • Nanjing University Top-Grade Scholarship, 2023, the highest honor in Nanjing University
  • National Scholarship, 2021, the highest honor in China's University

Copyright 2025 © Siheng Zhao