I am currently a first-year 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 research interests focus on embodied AI and foundation models. Specifically, I aim to harness the power of foundation models to build realistic world simulators that address the data bottlenecks in embodied AI. These simulations constrained by physical laws can, in turn, be used to train more powerful embodied foundation models, ultimately enabling artificial intelligence to operate more effectively in the real physical world.
If we can create simulators that mirror the real world with high fidelity, then we probably already be living in a virtual world ourselves.
Recent publications
Embodied Intelligence
HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments with Large Language Models
Qinhong Zhou*, Sunli Chen*, Yisong Wang, Haozhe Xu, Weihua Du, Hongxin Zhang, Yilun Du, Joshua B. Tenenbaum, Chuang Gan
ICLR 2024, also CVPR 2024 Embodied AI workshop challenge, arXiv, code, page
Building Cooperative Embodied Agents Modularly with Large Language Models
Hongxin Zhang, Weihua Du, Jiaming Shan, Qinhong Zhou, Yilun Du, Joshua B. Tenenbaum, Tianmin
ICLR 2024, also NeurIPS 2023 FMDM workshop, arXiv, code, page
Foundation Models
SALMON: Self-Alignment with Principle-Following Reward Models
Zhiqing Sun, Yikang Shen, Hongxin Zhang, Qinhong Zhou, Zhenfang Chen, David Cox, Yiming Yang, Chuang Gan
ICLR 2024, arXiv, code
Visual Chain-of-Thought Prompting for Knowledge-based Visual Reasoning
Zhenfang Chen*, Qinhong Zhou*, Yikang Shen, Yining Hong, Zhiqing Sun, Dan Gutfreund, Chuang Gan
AAAI 2024, arXiv, code
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
NeurIPS 2023, arXiv, code
Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Models
Qinhong Zhou, Zonghan Yang, Peng Li, Yang Liu
ACL 2023, arXiv, code
Service
- Organizer of the MVCS workshop (ECCV 2022, CVPR 2023)
- Reviewer of ICLR, CVPR, AAAI, ICML, IJCV, IEEE TIP, AACL, and IEEE Trans Multimedia.
Honors
- Scholarship of Overall Excellence, Tsinghua University
- Scholarship of Academic Excellence, Tsinghua University
- Excellent Graduate, Department of Computer Science and Technology, Tsinghua University