I'm a first-year Computer Science PhD student at Harvard. My research focuses on developing robust and scalable tools for AI post-training. I am very fortunate to be advised by Prof. Flavio du Pin Calmon.
Publications
Recent Research
Always happy to chat about research or potential collaborations! Check out my recent work below.
ICML 2nd Workshop on Models of Human Feedback for AI Alignment 2025
Inference-Time Reward Hacking in Large Language Models
Hadi Khalaf, Claudio Mayrink Verdun, Alex Oesterling, Himabindu Lakkaraju, Flavio du Pin Calmon
TL;DR: We characterize reward hacking in inference-time alignment methods like Best-of-n, introduce an efficient approximation of the optimal RLHF solution, and propose a hedging strategy to mitigate hacking.
ACM Conference on Fairness, Accountability, and Transparency (FAccT) 2025
🏆 Best Paper Award at the New England NLP Workshop
AI Alignment at Your Discretion
Maarten Buyl, Hadi Khalaf, Claudio Mayrink Verdun, Lucas Monteiro Paes, Caio C. Vieira Machado, Flavio du Pin Calmon
TL;DR: We risk deploying unsafe AI systems if we ignore their discretion in applying alignment objectives.
Education
Harvard University
Ph.D. in Computer Science
Advisor: Prof. Flavio Calmon
American University of Beirut
B.S. in Statistics and B.E. in Computer Engineering
Experience
Research Intern — Economics Department at Harvard
Advisor: Prof. Elie Tamer
Developed tools for counterfactual estimation in binary games.