I am currently a Ph.D. student at UMass Amherst advised by Prof. Chuang Gan. Before that, I am obtained my master degree at Tsinghua NLP advised by Prof. Yang Liu and my bachelor degree at CST@THU.
My current research focuses on embodied agentic frameworks, multi-turn post-training, and multi-agent systems.
🔥 News
- May 2026: I started at Google DeepMind as a student researcher, working on multi-turn agent post-training.
- Apr 2026: I gave an invited talk, Building Embodied Open-World Simulators, at Rutgers University.
- Sep 2025: I reached 1,000 citations.
Show less
- Jun 2025: 🔥🔥 We released Virtual Community!.
- Feb 2025: I will give a talk on my recent project Virtual Community at NYC Vision Day 2025.
- Jun 2024: I will give a talk on embodied decision-making in dynamically changing environments at zhidx.
- Jun 2024: I will join the panel discussion at The Fifth Embodied AI Workshop at CVPR 2024.
- May 2024: I will be presenting SALMON and HAZARD at ICLR 2024.
- Jul 2023: I will deliver an oral presentation on DBKD-PLM at ACL 2023.
- Jun 2023: Our team organized the second MVCS workshop at CVPR 2023.
- Jun 2023: I graduated from Tsinghua University again! It was a wonderful journey with the THU-NLP group.
- Oct 2022: Our team organized the first MVCS workshop at ECCV 2022, where I hosted the event.
Experience
May 2026 - Oct 2026: Student researcher at Google DeepMind. Research Topic: coding agent, multi-turn post-training.
May 2025 - Aug 2025: Research Intern at MERL. Research Topic: embodied multi-agent, post-training.
Mar 2024 - Jul 2024: Research intern at PKU-Agibot Lab.
Sep 2023 - Mar 2024: Research intern at ModelBest Inc.
Feb 2023 - Jun 2023: Research intern at Baidu Vision Group.
📝 Recent Publications
HARP-Bench: Benchmarking Robot Manipulation Around Active Humans
Qinhong Zhou*, Riley Zong*, Chunru Lin, Shivraj Singh Bhatti, Hongxin Zhang, Diyi Hu, Lin Qiu, Hanqing Zeng, Chuang Gan
Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation
Jiaben Chen, Sixun Dong, Qinhong Zhou, Raine Ma, Zhiyang Dou, Wojciech Matusik, Chuang Gan
Sentinel: Embodied Cooperative Spatial Reasoning and Planning
Xiangye Lin, Hongxin Zhang, Ruxi Deng, Qinhong Zhou, Chuang Gan
LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior
Qinhong Zhou, Chuang Gan, Anoop Cherian
Virtual Community: An Open World for Humans, Robots, and Society
Qinhong Zhou*, Hongxin Zhang*, Xiangye Lin*, Zheyuan Zhang*, Yutian Chen, Wenjun Liu, Zunzhe Zhang, Sunli Chen, Lixing Fang, Qiushi Lyu, Xinyu Sun, Jincheng Yang, Zeyuan Wang, Bao Chi Dang, Zhehuan Chen, Daksha Ladia, Jiageng Liu, Chuang Gan
Ella: Embodied Social Agents with Lifelong Memory
Hongxin Zhang, Zheyuan Zhang, Zeyuan Wang*, Zunzhe Zhang, Lixing Fang, Qinhong Zhou, Chuang Gan
Building Cooperative Embodied Agents Modularly with Large Language Models
Hongxin Zhang, Weihua Du, Jiaming Shan, Qinhong Zhou, Yilun Du, Joshua B. Tenenbaum, Tianmin Shu
Qinhong Zhou*, Sunli Chen*, Yisong Wang, Haozhe Xu, Weihua Du, Hongxin Zhang, Yilun Du, Joshua B. Tenenbaum, Chuang Gan
SALMON: Self-Alignment with Principle-Following Reward Models
Zhiqing Sun, Yikang Shen, Hongxin Zhang, Qinhong Zhou, Zhenfang Chen, David Cox, Yiming Yang, Chuang Gan
Visual Chain-of-Thought Prompting for Knowledge-based Visual Reasoning
Zhenfang Chen*, Qinhong Zhou*, Yikang Shen, Yining Hong, Zhiqing Sun, Dan Gutfreund, Chuang Gan
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
Zhiqing Sun, Yikang Shen, Qinhong Zhou, Hongxin Zhang, Zhenfang Chen, David Cox, Yiming Yang, Chuang Gan
Qinhong Zhou, Zonghan Yang, Peng Li, Yang Liu
AdaDS: Adaptive Data Selection for Accelerating Pre-trained Language Model Knowledge Distillation
Qinhong Zhou, Peng Li, Yang Liu, Yuyang Guan, Qizhou Xing, Ming Chen, Maosong Sun