Hong, R., Ovalle A., Ung M., Spiliopoulou E., Sagun L., Williams A., & Ross, C. (2026). Automated bias blind spots: Examining stereotype associations in VLM-as-a-judge paradigms. In The 2026 ACM Conference on Fairness, Accountability, and Transparency; 2025 Workshop on Evaluating AI in Practice.
Hong, R., Eiger Y., Hutson, J., Keyes O., & Agnew, W. (2026). Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization. In Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems.
Hong, R., Hutson, J., Agnew, W., Huda, I., Kohno, T., & Morgenstern, J. (2026). A Common Pool of Privacy Problems: Legal and Technical Lessons from a Large-Scale Web-Scraped Machine Learning Dataset. In Proceedings of the Symposium on Computer Science and Law; Privacy Law Scholars Conference 2025. [media coverage]
Lee C. P., Hong, R., Jiang H. H., Plotnik A., Agnew W., Morgenstern, J. (2026). How do data owners say no? A case study of data consent mechanisms in web-scraped vision-language AI training datasets. In Proceedings of the AAAI Conference on Artificial Intelligence; NeurIPS 2025 Workshop on Regulatable ML.
Agnew, W., Barnett, J., Chu, A., Hong, R., Feffer, M., Netzorg, R., Jiang, H.H., Awumey, E., & Das, S. (2025). Sound Check: Auditing Audio Datasets. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society. [codebase]
Hong, R., Agnew, W., Kohno, T. & Morgenstern, J. (2024). Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp. In Proceedings of the ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization. [codebase]
Lee C. P., Hong, R., Morgenstern, J. (2024). Fairness through partial awareness: Evaluation of the addition of demographic information for bias mitigation methods. ICML 2024 Next Generation of AI Safety Workshop.
Hong, R., Kohno, T. & Morgenstern, J. (2023). Evaluation of targeted dataset collection on racial equity in face recognition. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society. [codebase] [media coverage]
Deng, Z., Ding, F., Dwork, C., Hong, R., Parmigiani, G., Patil, P., & Sur, P. (2020). Representation via representations: Domain generalization via adversarially learned invariant representations. Preprint. [codebase]