Zhouliang Yu (郁昼亮)

PhD Student, Chinese University of Hong Kong

Verifiable Recursive Self-Improvement
Large Language Models
Data Centric Learning in Pretraining and Reinforcement Learning

Email: zlyu25 at cse dot cuhk dot edu dot hk

[Email] [CV] [Google Scholar] [GitHub]

Zhouliang Yu

I'm Zhouliang Yu (郁昼亮), a PhD student at the SphereLab in the Chinese University of Hong Kong, advised by Prof. Weiyang Liu.

Previously, I pursued doctoral studies at HKUST under Academician Yike Guo. I have also conducted research at Alibaba's Tongyi Lab.

Research summary

Most of my research is about reinforcement learning, large language models, AI4Math, and embodied AI. Some papers are highlighted.

Publications

Mathematical Reasoning & AI4Math

Formalmath: Benchmarking formal mathematical reasoning of large language models
Zhouliang Yu, Ruotian Peng, Keyi Ding, Yizhe Li, Zhongyuan Peng, Minghao Liu, Yifan Zhang, Zheng Yuan, Huajian Xin, Wenhao Huang, Yandong Wen, Ge Zhang, Weiyang Liu
arXiv preprint arXiv:2505.02735, 2025
Kimina-prover preview: Towards large formal reasoning models with reinforcement learning
Haiming Wang, Mert Unsal, Xiaohan Lin, Mantas Baksys, Junqi Liu, Zhouliang Yu, et al.
arXiv preprint arXiv:2504.11354, 2025
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
Zhongyuan Peng, Yifan Yao, Kaijing Ma, Shuyue Guo, Yizhe Li, Yichi Zhang, Chenchen Zhang, Yifan Zhang, Zhouliang Yu, et al.
arXiv preprint arXiv:2507.06181, 2025

Large Language Models

Map-neo: Highly capable and transparent bilingual large language model series
Ge Zhang, Scott Qu, Jiaheng Liu, Chenchen Zhang, Chenghua Lin, Chow Leuang Yu (Core Contributor, authored with my Cantonese name), et al.
Technical Report, 2024
Chinese tiny llm: Pretraining a chinese-centric large language model
Xinwei Du, Zhouliang Yu (Co-First Author), Songyang Gao, Ding Pan, Yuyang Cheng, Ziyang Ma, Ruibin Yuan, Xingwei Qu, Jiaheng Liu, Tianyu Zheng, Xinchen Luo, Guorui Zhou, Wenhu Chen, Ge Zhang
Conference on Language Modeling, 2024
Codeeditorbench: Evaluating code editing capability of large language models
Jiawei Guo, Ziming Li, Xueling Liu, Kaijing Ma, Tianyu Zheng, Zhouliang Yu, Dawei Pan, Yizhi Li, Ruibo Liu, Yue Wang, Shuyue Guo, et al.
arXiv preprint arXiv:2404.03543, 2024

Reinforcement Learning

Asp: Learn a universal neural solver!
Chenguang Wang, Zhouliang Yu, Stephen McAleer, Tianshu Yu, Yaodong Yang
IEEE Transactions on Pattern Analysis and Machine Intelligence, 46 (6), 4102-4114, 2024
Generating Symbolic World Models via Test-time Scaling of Large Language Models
Zhouliang Yu, Yuhuan Yuan, Tim Z. Xiao, Fuxiang Frank Xia, Jie Fu, Ge Zhang, Ge Lin, Weiyang Liu
Transactions on Machine Learning Research, 2025

Embodied AI & Robotics

ManiFoundation Model for General-Purpose Robotic Manipulation of Contact Synthesis with Arbitrary Objects and Robots
Zhixuan Xu, Chongkai Gao, Zixuan Liu, Gang Yang, Chenrui Tie, Haozhuo Zheng, Haoyu Zhou, Weikun Peng, Debang Wang, Tianrun Hu, Tianyi Chen, Zhouliang Yu, Lin Shao
International Conference on Intelligent Robots and Systems (Oral), 2024
Multireact: Multimodal tools augmented reasoning-acting traces for embodied agent planning
Zhouliang Yu, Jie Fu, Yue Mu, Chenguang Wang, Lin Shao, Yaodong Yang
Robot Learning Workshop at NeurIPS 2023 (Oral), 2023