I am currently pursuing my Ph.D. degree in the Joint Training Program between Fudan University (FDU) and Shanghai AI Laboratory, under the supervision of Prof. Dacheng Tao, and I expect to graduate in 2027. Prior to this, I completed my undergraduate studies in the Department of Computer Science and Technology at Fudan University, where I graduated and obtained my Bachelor’s degree in 2022 under the guidance of Prof. Qi Zhang. I sincerely appreciate the invaluable guidance, support, and inspiration that all my mentors have provided throughout my academic journey.

I have authored or co-authored more than ten papers published in top-tier international journals and conferences, including IEEE TPAMI, ICML, NeurIPS, ICLR and ACL. My current research interests focus on reinforcement learning (RL) for generative large language models (LLMs), specifically including reinforcement learning from human feedback (RLHF), reasoning RL, and agentic RL. My earlier research mainly centered on the inference robustness of discriminative language models.

📧 I am open to collaboration and welcome inquiries from anyone interested in my research topics. Feel free to reach out via rbao2018@outlook.com or rbao22@m.fudan.edu.cn.

🔥 News

• 2025.11:  🎉🎉 One paper has been accepted by AAAI 2026.
• 2025.09:  🎉🎉 One paper has been accepted by NeurIPS 2025.
• 2025.05:  🎉🎉 One paper has been accepted by ACL 2025.
• 2025.01:  🎉🎉 One paper has been accepted by ICLR 2025.
• 2024.09:  🎉🎉 One paper has been accepted by NeurIPS 2024.
• 2023.05:  🎉🎉 One paper has been accepted by ACL 2023.
• 2022.05:  🎉🎉 One paper has been accepted by ACL 2022.

📝 Selected Publications

†: equal contribution, * : corresponding author

Conference Papers

• Time-Frequency Token Advantage Clipping for Training Efficient Large Reasoning Model

  Rong Bao, Bo Wang, Xiao Wang, Hongyu Li, Rui Zheng, Qi Zhang, Liang Ding, Dacheng Tao
  Association for the Advancement of Artificial Intelligence (AAAI), 2026
  [Paper][Code]

• Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections

  Bo Wang, Qinyuan Cheng, Runyu Peng, Rong Bao, Peiji Li, Qipeng Guo, Linyang Li, Zhiyuan Zeng, Yunhua Zhou, Xipeng Qiu
  Conference on Neural Information Processing System (NeurIPS), 2025
  [Paper][Code]

• Fixing Distribution Shifts of LLM Self-Critique via On-Policy Self-Play Training

  Rong Bao, Donglei Yu, Kai Fan, Minpeng Liao
  Association for Computational Linguistics (ACL), 2025
  [Paper][Code]

• InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling

  Yuchun Miao, Sen Zhang, Liang Ding, Rong Bao, Lefei Zhang, Dacheng Tao
  Conference on Neural Information Processing System (NeurIPS), 2024
  [Paper][Code]

• CASN: Class-Aware Score Network for Textual Adversarial Detection

  Rong Bao, Rui Zheng, Liang Ding, Qi Zhang, Dacheng Tao
  Association for Computational Linguistics (ACL), 2023
  [Paper][Code]

🎖 Honors and Awards

• Huawei Annual Scholarship, College of Computer Science and Artificial Intelligence, 2025 June
  (华为年度奖学金, Top 5% in Fudan University)
• Outstanding Bachelor Graduate of Fudan University, 2022 June
  (复旦大学优秀毕业生, Top 30% in Fudan University)

📖 Educations

• Fudan University, September 2022 – Present
  Ph.D. Candidate in the College of Computer Science and Artificial Intelligence, Shanghai, China.
  Supervised by Dacheng Tao.
• Fudan University, September 2018 – July 2022
  Undergraduate Student in the College of Computer Science and Artificial Intelligence, Shanghai, China.
  Supervised by Qi Zhang.

💻 Internships

• 2025.02 - 2026.02, Inclusion AI, Hangzhou.
• 2024.07 - 2025.01, Tongyi Lab, Beijing.
• 2023.04 - 2024.03, Shanghai AI Lab, Shanghai.