Michael Feffer, PhD Student
I am a fourth-year Societal Computing PhD student in the Software and Societal Systems Department (S3D) at Carnegie Mellon University. Supported in part by a GEM Fellowship, I am broadly interested in applying artificial intelligence and machine learning techniques to problem spaces in the humanities and social sciences. My current interests include algorithmic fairness, music information retrieval, participatory approaches to machine learning, AI for social good, and the ethics and evaluation of generative AI. Prior to coming to CMU, I graduated with a Master of Engineering (MEng) degree from MIT for work I did in the MIT Media Lab's Affective Computing Group with Prof. Rosalind Picard and Dr. Ognjen Rudovic, and I additionally conducted undergraduate research with Prof. Randall Davis in the Computer Science and Artificial Intelligence Laboratory (CSAIL). I also worked as a software engineer at Mastercard Data & Services for 2.5 years after graduating from MIT.
Research Interests: Fairness in Machine Learning, AI for Social Good, Music Information Retrieval, Participatory Machine Learning, GenAI Evaluation
Publications
Just Label the Repeats for In-The-Wild Audio-to-Score Alignment
Irmak Bukey, Michael Feffer, Chris Donahue
International Society for Music Information Retrieval Conference (ISMIR), 2024Red-Teaming for Generative AI: Silver Bullet or Security Theater?
Michael Feffer, Anusha Sinha, Wesley H. Deng, Zachary Lipton, Hoda Heidari
AAAI/ACM Conference on Artificial Intelligence, Ethics and Society (AIES), 2024Prompt Exploration with Prompt Regression
Michael Feffer*, Ronald Xu*, Yuekai Sun, Mikhail Yurochkin
Conference on Language Modeling (COLM), 2024DeepDrake ft. BTS-GAN and TayloRVC: A Survey of Musical Deepfake Models
Michael Feffer, Zachary Lipton, Chris Donahue
Workshop on Human-Centric Music Information Research (HCMIR@ISMIR), 2023The AI Incident Database as an Educational Tool to Raise Awareness of Harms: A Classroom Exploration of Efficacy, Limitations, & Future Design Improvements
Michael Feffer, Nikolas Martelaro, Hoda Heidari
ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO), 2023From Preference Elicitation to Participatory ML: A Critical Survey & Guidelines for Future Research
Michael Feffer, Michael Skirpan, Zachary Lipton*, Hoda Heidari*
AAAI/ACM Conference on Artificial Intelligence, Ethics and Society (AIES), 2023A Suite of Fairness Datasets for Tabular Classification
Martin Hirzel, Michael Feffer
arXiv, 2023Moral Machine or Tyranny of the Majority?
Michael Feffer, Hoda Heidari*, Zachary Lipton*
Association for the Advancement of Artificial Intelligence (AAAI), 2023Searching for Fairer Machine Learning Ensembles
Michael Feffer, Martin Hirzel, Samuel C. Hoffman, Kiran Kate, Parikshit Ram, Avraham Shinnar
International Conference on Automated Machine Learning (AutoML), 2023Assistive alignment of in-the-wild sheet music and performances
Michael Feffer, Zachary Lipton, Chris Donahue
23rd Int. Society for Music Information Retrieval Conf. (ISMIR LBD), 2022