Mycal Tucker

I am a graduate student in Julie Shah's Interactive Robotics Group (IRG) at MIT. In my research, I focus primarily on interpretability of AI systems. This manifests itself as custom-built neural models for particular tasks like fair classification, probes to understand the linguistic properties of NLP models, and representation learning for human understanding.

Before joining IRG, I worked for two years as a software engineer on the Advanced Projects team at Amazon Robotics, designing and testing warehouse allocation algorithms. Prior to that, I got my Masters in Engineering in the Robust Robotics Group at the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT, concentrating in robotics. My research adviser was Professor Nicholas Roy in the Department of Aeronautics and Astronautics.

Prior to joining CSAIL as a graduate student, I earned my BS in Electrical Engineering and Computer Science and Aeronautical and Astronautical Engineering from MIT in 2015.

Recent

I spent much of the 2021 focusing on two prongs of research: causal probing of large langauge models, and emergent communication. In the causal probing work , we developed a method to find when language models do (and don't) use representations of syntax causally. In the emergent communication work , we developed word-embedding-like tokens that agents in multi-agent settings used to communicate.

In addition to enrolling in courses, I also teach. I am the 2021-2022 AeroAstro Teaching Development Fellow, tasked with improving teaching in the department. I have TA'd 4 times in 3 departments: Intro to AI, Real Time Systems and Software, and Computational Psycholinguistics.