Author

Zifan Peng

Observed names: PENG, Zifan, Peng, Zifan

Institutions: Hong Kong University of Science and Technology, The Hong Kong University of Science and Technology (Guangzhou), Newcastle University, South China University of Technology

Observed institutions: Hong Kong University of Science and Technology, Fudan University, The Hong Kong University of Science and Technology (Guangzhou), Newcastle University, South China University of Technology

OpenAlex ID: A5077992181

Combating the COVID-19 infodemic using Prompt-Based curriculum learning

2023 · Zifan Peng, Mingchen Li, et al. · Expert Systems with Applications · 27

PDF

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

2025 · P Team, Du, Xinrun, et al. · arXiv (Cornell University) · 4

PDF

NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents

2025 · Ding, Jingzhe, Long, Shengda, et al. · arXiv (Cornell University) · 1

PDF

Source Coverage and Citation Bias in LLM-based vs. Traditional Search Engines

2025 · Zhang, Peixian, Ye, Qiming, et al. · arXiv (Cornell University) · 1

PDF

GasAgent: A Multi-Agent Framework for Automated Gas Optimization in Smart Contracts

2025 · Zheng, Jingyi, Peng, Zifan, et al. · arXiv (Cornell University) · 1

PDF

Enhanced Structured Lasso Pruning with Class-wise Information

2025 · Liu, Xiang, Li, Mingchen, et al. · arXiv (Cornell University) · 1

PDF

Prompt-based contrastive learning to combat the COVID-19 infodemic

2025 · Zifan Peng, Mingchen Li, et al. · Machine Learning · 1

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

2025 · Xeron Du, Yifan Yao, et al. · neural information processing systems · 1

CHASM: Unveiling Covert Advertisements on Chinese Social Media

2025 · Jingyi Zheng, Tianyi Hu, et al. · neural information processing systems · 1

Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference

2026 · Li, Mingchen, Peng, Zifan, et al. · arXiv (Cornell University)

PDF

TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation

2026 · Zheng, Jingyi, Liu, Yule, et al. · arXiv (Cornell University)

PDF

Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis

2026 · Li, Mingchen, Qiu, Meikang, et al. · arXiv (Cornell University)

PDF

What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media

2026 · Peng, Zifan, Huang, Yini, et al. · arXiv (Cornell University)

PDF

Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network

2026 · Ye, Qiming, Zhang, Peixian, et al. · arXiv (Cornell University)

PDF

On the Generation and Mitigation of Harmful Geometry in Image-to-3D Models

2026 · Liu, Yule, Yang, Yilong, et al. · arXiv (Cornell University)

PDF

CHASM: Unveiling Covert Advertisements on Chinese Social Media

2026 · Zheng, Jingyi, Hu, Tianyi, et al. · arXiv (Cornell University)

PDF

"What Did It Actually Do?": Understanding Risk Awareness and Traceability for Computer-Use Agents

2026 · Peng, Zifan, Li, Mingchen · arXiv (Cornell University)

PDF

Auditing Data Membership in Reinforcement Learning With Verifiable Rewards

2025 · Liu, Yule, Zhang, Heyi, et al. · arXiv (Cornell University)

PDF

"I Can See Forever!": Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments

2025 · Zhang, Ziyi, Sun, Zhen, et al. · arXiv (Cornell University)

PDF

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search

2025 · Luo, Zeren, Peng, Zifan, et al. · arXiv (Cornell University)

PDF

Prompt-Based Contrastive Learning to Combat the COVID-19 Infodemic

2024 · Zifan Peng, Mingchen Li, et al. · IEEE International Conference on Data Science and Advanced Analytics (DSAA)

Works count: 26

Citation count: 40

H-index: 2

I10-index: 1