Guozheng Ma

PhD student, Nanyang Technological University

Joined

November 2021

Names

Guozheng Ma (Preferred)

Emails

****@mails.tsinghua.edu.cn (Confirmed)

****@gmail.com (Confirmed)

****@e.ntu.edu.sg (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

PhD student

Nanyang Technological University (ntu.edu.sg)

2024 – Present

MS student

Tsinghua University (tsinghua.edu.cn)

2021 – 2024

Undergrad student

Hunan University (hnu.edu.cn)

2017 – 2021

Advisors, Relations & Conflicts

PhD Advisor

Dacheng Tao

2024 – Present

Expertise

Deep Reinforcement Learning

2021 – Present

Publications

The State of Reinforcement Finetuning for Transformer-based Agents
Shengchao Hu, Peng Wang, Guozheng Ma, Shi Fu, Li Shen, Ya Zhang, Dacheng Tao
- ICLR 2026 Poster
- Readers: Everyone
Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning
Guozheng Ma, Lu Li, Zilin Wang, Haoyu Wang, Shengchao Hu, Leszek Rutkowski, Dacheng Tao
- Submitted to ICLR 2026
- Readers: Everyone
UltraHorizon: Benchmarking LLM-Agent Capabilities in Ultra Long-Horizon Scenarios
Haotian Luo, Huaisong Zhang, Xuelin Zhang, Haoyu Wang, Zeyu Qin, WenJie Lu, Guozheng Ma, Haiying He, Yingsha Xie, Qiyang Zhou, Zixuan Hu, Hongze Mi, Yibo Wang, Naiqiang Tan, Hong Chen, Yi R. Fung, Chun Yuan, Li Shen
- Submitted to ICLR 2026
- Readers: Everyone
A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
Junjie Zhang, Guozheng Ma, Shunyu Liu, Haoyu Wang, Jiaxing Huang, Ting-En Lin, Fei Huang, Yongbin Li, Dacheng Tao
- NeurIPS 2025 ER Workshop
- Readers: Everyone
A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
Junjie Zhang, Guozheng Ma, Shunyu Liu, Haoyu Wang, Jiaxing Huang, Ting-En Lin, Fei Huang, Yongbin Li, Dacheng Tao
- ICLR 2026 Poster
- Readers: Everyone
Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
Yilun Kong, Guozheng Ma, Qi Zhao, Haoyu Wang, Li Shen, Xueqian Wang, Dacheng Tao
- MCDC @ ICLR 2025
- Readers: Everyone
Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
Yilun Kong, Guozheng Ma, Qi Zhao, Haoyu Wang, Li Shen, Xueqian Wang, Dacheng Tao
- ICML 2025 poster
- Readers: Everyone
Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
Guozheng Ma, Lu Li, Zilin Wang, Li Shen, Pierre-Luc Bacon, Dacheng Tao
- ICML 2025 oral
- Readers: Everyone
Are Large Language Models Really Robust to Word-Level Perturbations?
Haoyu Wang, Guozheng Ma, Cong Yu, Ning Gui, Linrui Zhang, Zhiqi Huang, Suwei Ma, Yongzhe Chang, Sen Zhang, Li Shen, Xueqian Wang, Peilin Zhao, Dacheng Tao
- Accepted by TMLR
- Readers: Everyone
Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping
Haoyu Wang, Guozheng Ma, Ziqiao Meng, Zeyu Qin, Li Shen, Zhong Zhang, Bingzhe Wu, Liu Liu, Yatao Bian, Tingyang Xu, Xueqian Wang, Peilin Zhao
- ICML 2024 Workshop MHFAIA Poster
- Readers: Everyone

View all 17 publications

Co-Authors

View all 62 co-authors