Zihan Ma

I am a Ph.D. student at Xi'an Jiaotong University under the supervision of Prof. Minnan Luo, working on machine learning and artificial intelligence. My research focuses on multimodal social network analysis and LLM evaluation, with applications to information security and social network analysis. Recently, I have been studying code generation and evaluation with LLMs.

My work involves developing advanced machine learning methods for detecting and interpreting bots and misinformation in social networks, particularly leveraging large language models and multimodal techniques. My research has been published at top-tier conferences such as NeurIPS, ACL, and SIGIR. Previously, I was a research intern with the OpenCompass team at Shanghai AI Lab.

I am particularly interested in explainable AI, LLM-based code generation, agent safety, and the intersection of machine learning with social media analysis. I am currently at Nanyang Technological University, Singapore, as part of a joint Ph.D. program. I always welcome collaboration and exchange in these research areas.