Hello, I am Zihan Luo, currently an Assistant Researcher at Chongqing University (CQU) . I received my Ph.D. degree in Computer Science from Huazhong University of Science and Technology (HUST) in 2026, where I was fortunate to be supervised by Professor Hong Huang (黄宏) and Principal Researcher Jianxun Lian (练建勋) from Microsoft Research Asia . Before that, I received my Bachelor degree in Electronic Engineering from HUST in 2020, and was fortunate to work closely with Professor Rui Yin (尹睿) from the University of Florida . During my academic journey, I also enriched my research experience through internships at Zhipu AI (focusing on LLM Alignment for Machine Learning Engineering) and OPPO (working on LLM-based in-conversation recommendation). I actively serve the academic community as a reviewer for top-tier venues such as NeurIPS, KDD, WWW, COLM, and Frontiers of Computer Science.

My research broadly lies at the intersection of Large Language Models (LLMs) and Graph Data Mining. I am deeply passionate about building AI systems that are not only intelligent but also robust, reliable, and beneficial to society. My current research focuses on:

• Trustworthy AI: Enhancing the fairness, robustness, and interpretability of Graph Neural Networks and LLMs against biases and adversarial attacks.
• Societal AI & Alignment: Calibrating and aligning large language models with human preference and exploring the mutual enhancement between complex AI systems and interdisciplinary fields such as sociology and psychology.

✨ Prospective Students & Collaborators:

I am always on the lookout for highly self-motivated undergraduate and graduate students to join my research group. If you are passionate about LLMs, data mining, or trustworthy AI, and are driven by a strong curiosity to solve impactful real-world problems, I would love to hear from you! Please feel free to drop me an email with your CV and a brief introduction of your background. You can check my full publication list on google scholar .

🔥 News

📝 Publications

• [Preprint] Yujiang Li, Zhenyu Hou, Xiaohan Jia, Zihan Luo, Zhilei Bei, Rui Lu, Hong Huang, Jie Tang, Yuxiao Dong. MLE-RL: Reinforcement Learning for Self-Improvement in Machine Learning Agents. Under review. [PAPER][CODE]

• [Preprint] Zihan Luo, Lingkui Chen, Ruike Zhang, Hong Huang, Boyang Zhang, Ziniu Chen, Lizhong Wang. ToolRec: Calibrated Preference Alignment for Query Recommendation in On-Device Assistants. Under review. [PAPER]

• [ACL’26] Zihan Luo, Hong Huang, Jianxun Lian, Yu Chang, Xing Xie, Hai Jin. Can AI Revise Research Papers with Human Review Feedback? An Empirical Study and Benchmark. In Findings of Annual Meeting of the Association for Computational Linguistics (ACL), 2026. (CCF-A)[PAPER] [CODE]

• [Frontiers of Computer Science] Zihan Luo, Xiran Song, Hong Huang, Jianxun Lian, Chenhao Zhang, Jinqi Jiang, Xing Xie, Hai Jin. GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability. In Frontiers of Computer Science (FCS), 2025. (CCF-T1) [PAPER] [CODE]

• [KDD’25] Zihan Luo, Hong Huang, Jianxun Lian, Xiran Song, Hai Jin. Towards Controllable Hybrid Fairness in Graph Neural Networks. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025. (CCF-A) [PAPER]

• [NeurIPS’24] Zihan Luo, Hong Huang, Yongkang Zhou, Jiping Zhang, Nuo Chen, Hai Jin. Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections. In Annual Conference on Neural Information Processing Systems (NeurIPS), 2024. (CCF-A) [PAPER] [CODE] [AI-TIME]

• [NeurIPS’23] Zihan Luo, Hong Huang, Jianxun Lian, Xiran Song, Xing Xie, Hai Jin. Cross-links Matter for Link Prediction: Rethinking the Debiased GNN from a Data Perspective. In Annual Conference on Neural Information Processing Systems (NeurIPS), 2023. (CCF-A) [PAPER] [CODE]

• [WWW’23] Xiran Song, Jianxun Lian, Hong Huang, Zihan Luo, Wei Zhou, Xue Lin, Mingqi Wu, Chaozhuo Li, Xing Xie, Hai Jin. xGCN: An Extreme Graph Convolutional Network for Large-scale Social Link Prediction. In ACM Web Conference (WWW), 2023. (CCF-A) [PAPER] [CODE] [Youtube]

• [Journal of Biomedical Informatics] Rui Yin*, Zihan Luo*, Pei Zhuang, Chee Keong Kwoh, Zhuoyi Lin. ViPal: A Framework for Virulence Prediction of Influenza Viruses with Prior Viral Knowledge Using Genomic Sequences. In Journal of Biomedical Informatics (JBI), 2023. (CCF-C) [PAPER] [CODE]

• [WSDM’22] Zihan Luo, Jianxun Lian, Hong Huang, Xing Xie, Hai Jin. Ada-GNN: Adapting to Local Patterns for Improving Graph Neural Networks. In ACM International Conference on Web Search and Data Mining (WSDM), 2022. (CCF-B) [PAPER] [CODE]

• [Current Genomics] Rui Yin, Zihan Luo, Chee Keong Kwoh. Exploring the Lethality ofHuman-adapted Coronavirus through Alignment-free Machine Learning Approaches Using Genomic Sequences. In Current Genomics, 2021. [PAPER] [CODE]

• [Bioinformatics] Rui Yin, Zihan Luo, Pei Zhuang, Zhuoyi Lin, Chee Keong Kwoh. VirPreNet: A Weighted Ensemble Convolutional Neural Network for the Virulence Prediction of Influenza A Virus Using All Eight Segments. In Bioinformatics, 2021. (CCF-A) [PAPER] [CODE]