Scholar
Xuan Kan
Google Scholar ID: SiD9eLgAAAAJ
Meta Platforms, Inc
Citations & Impact
Citations
979
H-index
14
i10-index
15
Publications
20
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- - Paper 'Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting' accepted to NeurIPS 2023
- - Paper 'Dynamic Brain Transformer with Multi-level Attention for Functional Brain Network Analysis' accepted to IEEE BHI 2023
- - Paper 'R-Mixup: Riemannian Mixup for Biological Networks' accepted to KDD 2023
- - Paper 'Multi-task Learning for Brain Network Analysis in the ABCD study' accepted to The IEEE-EMBS International Conference on Biomedical and Health Informatics
- - Paper 'Brain Network Transformer' accepted to NIPS 2022
- - Paper 'FBNetGen: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generation' accepted to MIDL 2022
Research Experience
- - Meta Monetization GenAI: Research Scientist, focusing on the application of Generative AI in advertising
- - Smart City Group (SenseTime): Intern, improving neural network efficiency through Neural Architecture Search techniques
- - University of Oxford: Undergraduate research on pervasive and trustworthy systems design and implementation using machine learning methods
Education
- - Ph.D. in Computer Science from Emory University, supervised by Prof. Carl Yang and Prof. Ying Guo
- - Bachelor's degree in Software Engineering from Tongji University, Shanghai, where research focused on pervasive and trustworthy systems design and implementation using machine learning methods, supervised by Prof. Xiaoxuan Lu at the University of Oxford
Background
- Currently a Research Scientist at Meta Monetization GenAI, working on building next-generation advertising systems that serve billions of users through Generative AI technology. Specifically, focusing on improving the quality of AI-generated advertisements and enhancing overall advertising performance metrics. During the doctoral research, the goal was to design more efficient and interpretable machine learning algorithms for fMRI data, which can assist in neurobiological findings and mental disease diagnosis.
