Zheyuan Zhang

Zheyuan "Brian" Zhang

First-year Ph.D. student in Computer Science at Johns Hopkins University, advised by Prof. Tianmin Shu and Prof. Daniel Khashabi.

Previously M.S. in Robotics and Graduate Certificate in Cognitive Science at University of Michigan, advised by Prof. Joyce Chai; B.S. in Computer Science at UMass Amherst.

Email CV Scholar Twitter Github

Research

I work at the intersection of artificial intelligence and cognitive science, with the goal of understanding how to make machines more human-like and how the brain works. My research focuses on Embodied AI and Continual Learning, along with natural language processing, skill learning, world models, and representation learning, to build scalable cognitive agents that can perceive, act, and learn continuously and sample-efficiently in physical and virtual environments. I am also interested in developmental psychology, behavioral emergence, and consciousness.

News

Selected Projects

img_agentodyssey
AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
Zheyuan Zhang*, Zehao Wen*, Alvin Zhang, Andrew Wang, Jianwen Xie, Daniel Khashabi†, Tianmin Shu†
Project Page Paper Code Documentation
img_vico
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
International Conference on Learning Representations (ICLR), 2026
Project Page Paper Code
img_mindjourney
MindJourney: Test-Time Scaling with World Models for Spatial Reasoning
Yuncong Yang*, Jiageng Liu*, Zheyuan Zhang, Siyuan Zhou, Reuben Tan, Jianwei Yang, Yilun Du, Chuang Gan
Conference on Neural Information Processing Systems (NeurIPS), 2025
Project Page Paper Code
img_comfort
Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities
Zheyuan Zhang*, Fengyuan Hu*, Jayjun Lee*, Freda Shi, Parisa Kordjamshidi, Joyce Chai, Ziqiao Ma
International Conference on Learning Representations (ICLR), 2025 (Oral)
Project Page Paper Code Dataset
img_combo
COMBO: Compositional World Models for Embodied Multi-Agent Cooperation
Hongxin Zhang*, Zeyuan Wang*, Qiushi Lyu*, Zheyuan Zhang, Sunli Chen, Tianmin Shu, Behzad Dariush, Kwonjoon Lee, Yilun Du, Chuang Gan
International Conference on Learning Representations (ICLR), 2025
Project Page Paper Code
img_ella
Ella: Embodied Lifelong Learning Agents with Non-Parametric Memory
Hongxin Zhang*, Zheyuan Zhang*, Zeyuan Wang*, Zunzhe Zhang, Lixing Fang, Qinhong Zhou, Chuang Gan
MAS Workshop @ ICML, 2025
Project Page Paper Code