Publications

You check out on the Google Scholar .

*Equal contribution

2026

• Shuhan Zhang, Zifan Peng, Yinwang Ren . GPLab: A Generative Agent-Based Framework for Policy Simulation and Evaluation. Journal of Artificial Societies & Social Simulation, 29(1), 1. DOI PDF

• Zifan Peng, Yule Liu, Zhen Sun, Mingchen Li, Zeren Luo, Jingyi Zheng, Wenhan Dong, Xinlei He, Xuechao Wang, Yingjie Xue, Shengmin Xu, Xinyi Huang . JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models The International Conference on Learning Representations (ICLR) 2026 DOI

• Zifan Peng, Jingyi Zheng, Yule Liu, Huaiyu Jia, Qiming Ye, Jingyu Liu, Xufeng Yang, Mingchen Li, Qingyuan Gong, Xuechao Wang, Xinlei He. . MATEX: A Multi-Agent Framework for Explaining Ethereum Transactions. Arxiv 2512.06933 DOI

2025

• Zifan Peng, etc. . NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents. Arxiv 2512.12730 DOI

• Peixian Zhang*, Qiming Ye*, Zifan Peng, Kiran Garimella, Gareth Tyson . Source Coverage and Citation Bias in LLM-based vs. Traditional Search Engines. Arxiv 2512.09483 DOI

• Yule Liu, Heyi Zhang, Jinyi Zheng, Zhen Sun, Zifan Peng, Tianshuo Cong, Yilong Yang, Xinlei He, Zhuo Ma . GRPO Privacy Is at Risk: A Membership Inference Attack Against Reinforcement Learning With Verifiable Rewards. Arxiv 2511.14045 DOI

• Jingyi Zheng*, Tianyi Hu*, Yule Liu, Zhen Sun, Zongmin Zhang, Wenhan Dong, Zifan Peng, Xinlei He . CHASM: Unveiling Covert Advertisements on Chinese Social Media. NeurIPS ‘25 DOI

• M-A-P Team et al., including Zifan Peng . SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines. NeurIPS ‘25 DOI
• Zeren Luo*, Zifan Peng*, Yule Liu, Zhen Sun, Mingchen Li, Jingyi Zheng, Xinlei He . Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search. USENIX Security ‘25 DOI
• Jingyi Zheng*, Zifan Peng*, Yule Liu, Junfeng Wang, Yifan Liao, Wenhan Dong, Xinlei He . GasAgent: A Multi-Agent Framework for Automated Gas Optimization in Smart Contracts. arXiv:2507.15761 DOI

• Zifan Peng, Yingjie Xue, and Jingyu Liu . Cross-Chain Options: A Bridgeless, Universal, and Efficient Approach. IEEE International Conference on Web Services (ICWS) ‘25 DOI

• Wenhan Dong, Zhen Sun, Yuemeng Zhao, Zifan Peng, Jun Wu, Jingyi Zheng, Yule Liu, Xinlei He, Yu Wang, Ruiming Wang, Xinyi Huang, Lei Mo . ZPD-SCA: Unveiling the Blind Spots of LLMs in Assessing Students’ Cognitive Abilities. arXiv:2508.14377 DOI
• Ziyi Zhang, Zhen Sun, Zongmin Zhang, Zifan Peng, Yuemeng Zhao, Zichun Wang, Zeren Luo, Ruiting Zuo, Xinlei He . “I Can See Forever!”: Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments. arXiv:2505.04488 DOI
• Yule Liu, Jingyi Zheng, Zhen Sun, Zifan Peng, Wenhan Dong, Zeyang Sha, Shiwen Cui, Weiqiang Wang, Xinlei He . Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models. arXiv:2504.13626 DOI
• Wenhan Dong, Yuemeng Zhao, Zhen Sun, Yule Liu, Zifan Peng, Jingyi Zheng, Zongmin Zhang, Ziyi Zhang, Jun Wu, Ruiming Wang, Shengmin Xu, Xinyi Huang, Xinlei He . Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications. arXiv:2505.00049 DOI
• Xiang Liu, Mingchen Li, Xia Li, Leigang Qu, Zifan Peng, Yijun Song, Zemin Liu, Linshan Jiang, Jialin Li . Automatic Pruning via Structured Lasso with Class-wise Information. arXiv:2502.09125 DOI
• Zifan Peng, Mingchen Li, Yue Wang, and George T.S. Ho . Prompt-based contrastive learning to combat the COVID-19 infodemic. Machine Learning, 114 (1), 6. DOI
• Jingyu Liu, Yingjie Xue, Zifan Peng, Chao Lin, and Xinyi Huang . FairRelay: Fair and Cost-Efficient Peer-to-Peer Content Delivery through Payment Channel Networks. TDSC DOI

2024 and before

• Zifan Peng, Mingchen Li, Yue Wang, and George T.S. Ho . Combating the COVID-19 infodemic using Prompt-Based curriculum learning. Expert Systems with Applications, 229, 120501. DOI