Involved in several academic activities, such as serving as a Main Track Program Committee member for the Fortieth AAAI Conference on Artificial Intelligence (AAAI 2026) and a Main Track Reviewer for the Fourteenth International Conference on Learning Representations (ICLR 2026); published multiple preprints, including 'An Open-Ended Benchmark and Formal Framework for Adjuvant Research with MLLM' and others.
Research Experience
Contributed to PaddleScience by successfully deploying and integrating the widely-used Crystal Graph CNN (CGCNN) model; completed the implementation of crystal structure data preprocessing, graph network construction, training and prediction pipeline; wrote detailed case documentation and user guide; code merged into the official main repository.
Education
Received B.E. degree from the School of Space Science and Technology at Xidian University in 2021; earned Master's degree in Electronic Information from the National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences in 2024, both under the supervision of Prof. Cheng-Lin Liu; currently a PhD candidate jointly affiliated with the State Key Laboratory of Multimodal Artificial Intelligence Systems at the Institution of Automation, Chinese Academy of Sciences and Zhongguancun Academy, supervised by Prof. Cheng-Lin Liu.
Background
Research Interests: Artificial intelligence and deep learning methods, particularly at the intersection of large language models and adjuvant science (Ai for Adjuvant); fundamental theories of multimodal large language models, including reliable reasoning and inference acceleration. My work bridges AI theory with practical applications in scientific domains.