About

I’m Mason Nakamura, a fourth-year Ph.D. student in Computer Science at UMass Amherst, working in the College of Information and Computer Sciences (CICS) as a member of the Resource-Bounded Reasoning Lab, under the guidance of Professor Shlomo Zilberstein. I’m currently a research intern at Microsoft Research working on collaborative multi-agent systems. My research is funded by the NSF Graduate Research Fellowship where I work on multi-agent safety and alignment.

I’m interested in the following research areas:

• Emergent Behaviors of Multi-Agent Systems: What safety-relevant behaviors emerge in long-horizon multi-agent trajectories? How can such behaviors be monitored and mitigated?
• Safety Evaluations and Auditing of Multi-Agent Systems: How can we prevent catastrophic risks of multi-agent systems via online auditing techniques and robust offline evaluations?
• Improving Multi-Agent Coordination and Communication: How can we improve multi-agent coordination capabilities? Can we do so without expensive multi-agent reinforcement learning?

If you are interested in collaboration, let’s have a chat!

Previously, I had internships at the Center for Human-Compatible Artificial Intelligence (CHAI) / Berkeley Artificial Intelligence Research (BAIR) (Summer 2023) on building ethically-compliant autonomous systems using constrained deep reinforcement learning, CHAI/BAIR (Summer-Fall 2022) building a formal framework for computationally bounded agents, Moravian University (Summer 2021 NSF REU) working on extremal and spectral graph theory, and Michigan State University (Summer 2020 NSF REU) working on geometric deep learning.