Junyu Zhang

I am a Master's student in Computer Science (MSCS) at University of Illinois Urbana-Champaign, advised by Prof. Huan Zhang. Previously, I received my bachelor's degree from Huazhong University of Science and Technology. I am fortunate to work under the supervision of Prof. Chongjie Zhang in the Institute for Interdisciplinary Information Sciences at Tsinghua University and Prof. Chuang Gan in the MIT-IBM Watson AI Lab.

My research interests lies at Reinforcement Learning, Large Language Models and Embodied AI, with particular interests in building autonomous agents with generalizable ability to perceive, reason and interact with the real-world environment.

If you would like to discuss my research or potential collaborations further, feel free to contact me. I'm open to connect and collaborate with each other.

Email / CV (last updated: June 2025) / Google Scholar / Github / Twitter

News

2025/06 - We have released AlphaOne, a universal framework for modulating reasoning progress in large reasoning models at test time 🔥. Explore more on our website!
2025/06 - EmbodiedBench got accepted to ICML 2025 Oral 🔥. Check out our project page here.
2025/01 - DynaMath got accepted to ICLR 2025.
2024/01 - Our work about multi-cellular soft robot design got accepted to ICLR 2024.
2023/02 - Selected as the Outstanding undergraduates in Term of Academic Performance in 2022 (top 1%)!

Publications and Preprints

	AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time Junyu Zhang, Runpei Dong, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta, Huan Zhang Arxiv Preprint [Paper] [Website] Press: VentureBeat
	EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents Rui Yang, Hanyang Chen, Junyu Zhang, Mark Zhao, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, Heng Ji, Huan Zhang, Tong Zhang The Forty-second International Conference on Machine Learning (ICML Oral), 2025 [Paper] [Website] [Hugging Face]
	DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models Chengke Zou, Xingang Guo, Rui Yang, Junyu Zhang, Bin Hu, Huan Zhang The Thirteenth International Conference on Learning Representations (ICLR), 2025* [Paper] [Website] [Dataset]
	Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design Heng Dong, Junyu Zhang, Chongjie Zhang The Twelfth International Conference on Learning Representations (ICLR), 2024 [Paper] [Website]
	Symmetry-Aware Robot Design with Structured Subgroups Heng Dong, Junyu Zhang, Tonghan Wang, Chongjie Zhang The Fortieth International Conference on Machine Learning (ICML), 2023 [Paper] [Website]
	Offline Meta Reinforcement Learning with In-Distribution Online Adaptation Jianhao Wang, Jin Zhang, Haozhe Jiang, Junyu Zhang, Liwei Wang, Chongjie Zhang The Fortieth International Conference on Machine Learning (ICML), 2023 [Paper]

Honors and Awards

2024 - Outstanding Graduate Honor.
2022 - Outstanding Undergraduate Student Award (top 1%).
2022 - Science and Technology Innovation Scholarship.
2021 - The Second Prize of the World Robot Contest-BCI Brain Control Robot Contest.
2021 - Excellent Academic Scholarship.

Academic Services

Conference Reviewers:

ICLR 2025, NeurIPS 2025, ACL ARR 2025

Teaching Assistants:

ECE 598 - Advanced Topics in Machine Learning and Formal Methods, UIUC, Fall 2024

CS 441 - Applied Machine Learning, UIUC, Spring 2025