Minh Pham

I expect to graduate in 2026 and am actively seeking research scientist/engineer positions. If my expertise aligns with your needs, please feel free to contact me via email to request my latest resume.
I am a final year Ph.D. Candidate at New York University, under the supervision of Prof. Chinmay Hegde, and part of the Algorithms and Foundations Group. Prior to this, I obtained dual Bachelor’s degrees in Computer Science and Mathematical Sciences from Worcester Polytechnic Institute. During my undergraduate studies, I had the privilege of being mentored by Prof. Jacob Whitehill.
Research: The goal of my research is to build algorithms that make deep neural networks safer and easier to use. In particular, my current works center on understanding memorization in text-to-image generative models and how to mitigate it. Furthermore, I have dedicated efforts to fortify DNNs against adversarial attacks, distributional shifts, and label noise.
news
Sep 18, 2025 | Our work on understanding and characterizing concept erasure methods in text-to-image models has been accepted at NeurIPS 2025. |
---|---|
May 12, 2025 | I joined Amazon as an Applied Scientist Intern. |
Dec 15, 2024 | We are organizing the workshop on “Red Teaming GenAI: What Can We Learn from Adversaries?” at NeurIPS 2024. Check out the workshop website. |
Sep 16, 2024 | I joined Amazon as an Applied Scientist Intern. |
May 13, 2024 | I joined Snowflake as a Research Intern. |
Feb 26, 2024 | One paper accepted to CVPR 2024! |
Jan 15, 2024 | Our work on the vulnerability of concept erasure methods is out on is accepted to ICLR 2024. Check out our project website! |