Research Interests

I am interested in understanding the inner workings of foundational models. I believe we can leverage insights gained from understanding the representations these models construct during pretraining to drive the next major developments in the field.

Publications

From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP
EMNLP 2024
Marius Mosbach, {Vagrant Gautam, Tomás Vergara Browne}, Dietrich Klakow, Mor Geva

Eigenpruning: an Interpretability-Inspired PEFT Method (extended abstract)
LatinX Workshop @ NAACL 2024
Tomás Vergara Browne, Álvaro Soto, Akiko Aizawa

Large Language Models are biased to overestimate profoundness
EMNLP 2023
{Eugenio Herrera-Berg, Tomás Vergara Browne}, Pablo León-Villagrá, Marc Lluís-Vives, Cristian Buc Calderon

Talks

Interpretability and Analysis: An Overview and its Impact
Invited Talk @ AI Safety Initiative UC Chile

Experience

I worked for a long time as a software engineer at a YC startup, Fintoc. I met amazing and smart people, but in the end, I decided to go into ML research.

I have collaborated with researchers at CENIA. Our work has lead to a publication at the main event in EMNLP 2023.

I have done research at the NII in Japan, under the supervision of professor Akiko Aizawa. A bit of my work there has appeared in the LatinX workshop at NAACL 2024.

Teaching

Lecturer in ML for Computer Vision for the AI certificate of PUC
(December 2023 onwards)

Design and Analysis of Algorithms Teaching Assistant
(Spring 2023)

Linear Algebra Teaching Assistant (lectures in spanish)
(Fall 2020, Fall 2021)

Introduction to Programming Teaching Assistant
(Fall 2021)

Discrete Mathematics Teaching Assistant
(Spring 2020)

Other interests

I like reading Math, CS and Sci-fi books. You can check out some them here.

I really enjoy doing artistic gymnastics, although I am not great (but I'll get better over time).