About me

I’m Zongqi Wang. I am currently a second-year master’s student supervised by Prof.Yang at Tsinghua University. I received my bachelor’s degree from Xidian University. My previous research focused on AI Safety. Now, my research interests are primarily in Large Language Model, Reinforcement Learning, Reward Model, Generative Reward Model, Evaluation and Role-Playing.

🔥 News

• 2026.04: 🎉🎉 2 papers about Reward Model and LLM safety are accepted to ACL 2026 Main.
• 2026.01: 🎉🎉 1 paper about Reward Model is accepted to ICLR 2026 oral.
• 2025.08: 🎉🎉 1 paper about LLM safety is accepted to EMNLP 2026 oral.
• 2025.05: 🎉🎉 2 papers about LLM safety are accepted to ACL 2025 Main and Findings.

📝 Publications

⚖️ Reward Model

• Reward Modeling from Natural Language Human Feedback
  • Zongqi Wang, Rui Wang, Yuchuan Wu, Yiyao Yu, Pinyi Zhang, Shaoning Sun, Yujiu Yang, Yongbin Li
  • arXiv 2026.01 [pdf]
• P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
  • Pinyi Zhang, Ting-En Lin, Yuchuan Wu, Jingyang Chen, Zongqi Wang, Hua Yang, Ze Xu, Fei Huang, Kai Zhang, Yongbin Li
  • ICLR 2026 (Oral) [pdf]
• S2J: Bridging the Gap Between Solving and Judging Ability in Generative Reward Models
  • Shaoning Sun*, Jiachen Yu*, Zongqi Wang*, Xuewei Yang, Tianle Gu, Yujiu Yang
  • arXiv 2025.09 [pdf]
• SCAN: Structured Capability Assessment and Navigation for LLMs
  • Zongqi Wang, Tianle Gu, Chen Gong, Xin Tian, Siqi Bao, Yujiu Yang
  • ACL 2026 Main [project][pdf][code]

🛡️ LLM Safety

• Probing the robustness of large language models safety to latent perturbations
  • Tianle Gu, Kexin Huang, Zongqi Wang, Yixu Wang, Jie Li, Yuanqi Yao, Yang Yao, Yujiu Yang, Yan Teng, Yingchun Wang
  • ACL 2026 Main [pdf]
• Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking
  • Tianle Gu*, Zongqi Wang*, Kexin Huang, Yuanqi Yao, Xiangliang Zhang, Yujiu Yang, Xiuying Chen
  • EMNLP 2025 Main (Oral) [pdf][code]
• MorphMark: Flexible Adaptive Watermarking for Large Language Models
  • Zongqi Wang, Tianle Gu, Baoyuan Wu, Yujiu Yang
  • ACL 2025 Main [pdf][code]
• Robust and Minimally Invasive Watermarking for EaaS
  • Zongqi Wang, Baoyuan Wu, Jingyuan Deng, Yujiu Yang
  • ACL 2025 Findings [pdf][code]
• Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluations
  • Decheng Liu*, Zongqi Wang*, Chunlei Peng, Nannan Wang, Ruimin Hu, Xinbo Gao
  • AAAI 2025 [pdf][code]

💻 Internships

• 2025.06 - present, Alibaba Qwen Character.
• 2024.12 - 2025.05, Baidu ERNIE Bot NLP.

📖 Educations

• 2024.09 - 2027.06, Master’s degree (Expected), Tsinghua University
• 2020.09 - 2024.06, Bachelor’s degree, Xidian University