Iván Arcuschin Moreno

Iván Arcuschin Moreno

Independent Researcher

University of Buenos Aires

I’m a Computer Science PhD from University of Buenos Aires, Argentina. I’m passionate about Machine Learning and Software Engineering, two topics which I’ve studied in-depth during my PhD.

Right now, I’m fascinated by the way AI models are becoming incredibly common and making a big impact in society, even though we still don’t fully understand how they work. This has motivated me to dive deep into the field of Mechanistic Interpretability, taking part in the ML Alignment & Theory Scholars (MATS) program, where I’m working on a project to build a benchmark of semi-synthetic yet realistic transformers with known circuits for evaluating mechanistic interpretability techniques.

Interests

  • Mechanistic Interpretability
  • Automated Software Engineering

Education

  • PhD, 2024

    University of Buenos Aires

  • MSc, 2018

    University of Buenos Aires

Awards

Google Latin America Reserch Award 2018 (extension)

For the project: “Evolutiz: Multi-objective Test Generation for Testing Evolving Android Applications”. Professor: Juan Pablo Galeotti, Student: Iván Arcuschin Moreno.

Google Latin America Reserch Award 2017

For the project: “Evolutiz: Multi-objective Test Generation for Testing Evolving Android Applications”. Professor: Juan Pablo Galeotti, Student: Iván Arcuschin Moreno.