cv
My work experience -- I specialize in diffusion model research, and have pre-trained medium-to-large scale models (>2B parameters) on larger datasets (>1T tokens / >1B images).
Education
-
Ph.D. in Applied Mathematics
Yale University - Advised by Ronald Coifman and Yuval Kluger.
-
B.S. in Computer Science and Mathematics
Yale University
Experience
-
2024 Research Intern
ByteDance - Built multimodal image / language models on the AI Seed-Vision Team, with a focus on diffusion-based frameworks. Acquired large-scale datasets (100M+ images / text) and trained diffusion models for simultaneous text-to-image, image-to-text, and visual understanding. Results submitted to CVPR 2025. Mentors Heng Wang, Peng Wang, and Linjie Yang.
-
2024 Research Intern
Elucid - Developed multimodal foundation models to aid in generating and augmenting arterial CT imagery and segmentations for improved fractional flow reserve (FFR) analysis and cardiologist report generation.
-
2023 Research Intern
Bosch Center for Artificial Intelligence - Conducted research on robust training-free approaches to guided diffusion models using optimal control. Published at NeurIPS 2024. Mentor Marcus Pereira.
-
2020 Research Intern
Center for Computational Mathematics, Flatiron Institute - Explored deep image prior-based techniques for enhancing phase retrieval in low-photon settings at the Center for Computational Mathematics (CCM) at Flatiron Institute
-
2016 Software Engineering Intern
Amazon Lab126 - Modified machine learning module (an n-gram Markov model) in FireOS to reduce memory usage by ~2x with no significant reduction in prediction quality