Publications

• Lin, Xiaofeng, Xu, Chenheng, Yang, Matthew, and Cheng, Guang. "CTSyn: A Foundation Model for Cross Tabular Data Generation." International Conference on Learning Representations (2025).

• Lin, Xiaofeng, Han, Jun, Emami, Melika, Hill, Brian L., and Tillman, Robert E. "Synthetic Electronic Health Record Generation of Rare Disease With Reinforcement Learning." Workshop on Large Language Models and Generative AI for Health at AAAI 2025. 

• Xing, Yue, Lin, Xiaofeng, Song, Qifan, Xu, Yi, Zeng, Belinda, and Cheng, Guang. "Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective." International Conference on Artificial Intelligence and Statistics, 2024.

• Suh, Namjoon, Lin, Xiaofeng, Hsieh, Din-Yin, Honarkhah, Mehrdad, and Cheng, Guang. "AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing." In NeurIPS 2023 Workshop on Synthetic Data Generation with Generative AI, 2023.

• Lin, Xiaofeng, Kim, Seungbae, and Joo, Jungseock. "Fairgrape: Fairness-aware gradient pruning method for face attribute classification." European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2022.

• Lin, Xiaofeng, Kernell, Georgia, Groeling, Tim, Joo, Jungseock, Luo, Jun, and Steinert-Threlkeld, Zachary C. "Mask images on Twitter increase during COVID-19 mandates, especially in Republican counties." Scientific Reports 12, no. 1 (2022): 21331.

Preprints and Papers Under Review

• Lin, Xiaofeng, Kim, Seungbae, Li, Zhuoya, and Cheng, Guang. "Utility-Driven Tabular Data Synthesis via Reinforcement Learning." Submitted.

• Xing, Yue, Lin, Xiaofeng, Suh, Namjoon, Song, Qifan, and Cheng, Guang. "Benefits of transformer: In-context learning in linear regression tasks with unstructured data." arXiv preprint arXiv: 2402.00743, 2024.