Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training

Wang, K., Niu, H., Li, D. (2026). arXiv preprint arXiv:2602.16065. arXiv

Incorporating LLM Embeddings for Variation Across the Human Genome

Niu, H., Bryan, J., Li, X., Li, D. (2025). arXiv preprint arXiv:2509.20702. arXiv

Deep Generative Models: Complexity, Dimensionality, and Approximation

Wang, K., Niu, H., Wang, Y., Li, D. (2025). Journal of Machine Learning Research, 26(143), 1–37. JMLR

Incorporating LLM-Derived Information into Hypothesis Testing for Genomics Applications

Bryan, J. G., Niu, H., Li, D. (2025). bioRxiv. bioRxiv

Spatial Clustering for Carolina Breast Cancer Study

Niu, H., Troester, M., Li, D. (2024). Biocomputing 2025: Proceedings of the Pacific Symposium, 346–359. PSB

Applying a novel measure of community-level healthcare access to assess breast cancer care timeliness

Dunn, M. R., Niu, H., Li, D., Emerson, M. A., Thompson, C. A., Nichols, H. B., Roberson, M. L., Wheeler, S. B., Hyslop, T., Elston Lafata, J., et al. (2025). Cancer Epidemiology, Biomarkers & Prevention, 34(7), 1199–1209.

Customized blood-brain barrier shuttle peptide to increase AAV9 vector crossing the BBB and augment transduction in the brain

Zhang, X., Chai, Z., Dobbins, A. L., Itano, M. S., Askew, C., Miao, Z., Niu, H., Samulski, R. J., Li, C. (2022). Biomaterials, 281, 121340.

Adeno-associated virus-mediated expression of activated factor V (FVa) for hemophilia phenotypic correction

Sun, J., Chen, X., Chai, Z., Niu, H., Dobbins, A. L., Nichols, T. C., Li, C. (2022). Frontiers in Medicine, 9.