Zheyuan "Brian" Zhang

I am a first-year Ph.D. student in Computer Science at the Johns Hopkins University, advised by Prof. Tianmin Shu and Prof. Daniel Khashabi.

Before joining JHU, I graduated with an M.S. in Robotics from the Robotics Institute and a Graduate Certificate in Cognitive Science from the Weinberg Institute for Cognitive Science at the University of Michigan. I was a research assistant at the SLED lab, advised by Prof. Joyce Chai. I got my Bachelor's in Computer Science from College of Information & Computer Sciences, UMass Amherst.

zzhan378 [at] jhu [dot] edu / CV / Scholar / Twitter / Github

Research

I consider myself as a connectionist, and I am fascinated with understanding natural intelligence by creating something similar, through computational modeling with neural networks. My research interests center on Embodied AI, Multimodality, and Natural Language Processing, with the goal of creating scalable cognitive agents that perceive, act, and learn continuously and sample-efficiently from experiences, similar to humans in both physical and virtual worlds.

If you're a JHU student interested in topics like memory, continual learning, skill acquisition, spatial intelligence, world models, representation learning, developmental psychology, behavioral emergence, or consciousness, and you'd like to work with me, feel free to drop me an email to set up a chat.

News

[2025.08] Virtual Community accepted to ICLR 2026.
[2025.08] MindJourney accepted to NeurIPS 2025.
[2025.08] One paper accepted to EMNLP 2025.
[2025.06] We released Virtual Community — a simulator where humans and robots cohabit in dynamic, open societies with unlimited characters, robots, and cities!
[2025.01] COMFORT accepted to ICLR 2025 as Oral Presentation.

[2025.03] I will join Johns Hopkins University in Fall 2025.

[2025.01] COMBO accepted to ICLR 2025.

[2024.11] One paper accepted to COLING 2025.

[2024.10] COMFORT accepted to Pluralistic Alignment Workshop @ NeurIPS 2024.

[2024.10] EILeV accepted to Video-Language Models @ NeurIPS 2024.

[2024.09] EILeV accepted to EMNLP 2024.

[2023.10] HAR accepted to EMNLP 2023.

Publications and Preprints

* → equal contribution

	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
	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
	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
	Ella: Embodied Social Agents with Lifelong Memory Hongxin Zhang, Zheyuan Zhang, Zeyuan Wang, Zunzhe Zhang, Lixing Fang, Qinhong Zhou, Chuang Gan MAS Workshop @ ICML*, 2025 Project Page \| Paper \| Code
	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
	Explainable Procedural Mistake Detection Shane Storks, Itamar Bar-Yossef, Yayuan Li, Zheyuan Zhang, Jason J. Corso, Joyce Chai Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025 Paper \| Code
	A Combinatorial Approach to Neural Emergent Communication Zheyuan Zhang International Conference on Computational Linguistics (COLING), 2025 Paper
	EILeV: Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties Keunwoo Peter Yu, Zheyuan Zhang, Fengyuan Hu, Shane Storks, Joyce Chai Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024 Paper \| Code
	From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning Zheyuan Zhang, Shane Storks, Fengyuan Hu, Sungryull Sohn, Moontae Lee, Honglak Lee, Joyce Chai Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Paper \| Code
	Low-cost Solution for Vision-based Robotic Grasping Zheyuan Zhang, Huiliang Shang International Conference on Networking Systems of AI (INSAI), IEEE Computer Society, 2021 (Second Prize) Paper \| Code (110 )

Other Projects

Bot Lab: Autonomous Ground Vehicle from Low-level Control, SLAM to Planning and Exploration
Zheyuan Zhang, Yu Zhu, Manu Aatitya Raajan Priyadharshini, Thirumalaesh Ashokkumar
ROB 550 (Robotic Systems Laboratory), University of Michigan, 2022
Paper

Teaching

Graduate Student Instructor (GSI), EECS 492 (Introduction to Artificial Intelligence), University of Michigan
Winter 2024, Fall 2023

Textbook: Artificial Intelligence: A Modern Approach, 4th Edition

Academic Services

Conference Reviewer: ICLR 2025, NeurIPS 2024 Workshop

My hobbies

Movie & TV: suspense dramas and fantasy animes; Fan of "A Mortal's Journey" (凡人修仙传).
Gaming: competitive FPS games (Rainbow Six Siege, Valorant, etc). I achieved the highest ranks in R6s for 10 seasons (5x champion, 5x diamond).
Bodybuilding
HiFi: headphones, DACs, amplifiers
Fragrance

Source code borrowed from Jon Barron's website.