Juan David Guerra

Juan David Guerra

M.ASc Student in Software Engineering

Mila - Quebec AI Institute & Polytechnique Montréal

Developing amortized ML techniques for applications to Neuroprosthetics. Recipient of NSERC CGS-M and FRQNT Master's scholarships.

About Me

I am an M.ASc student in Software Engineering at Polytechnique Montréal and Mila - Quebec AI Institute (GPA: 4.0/4.0), supervised by Professor Marco Bonizzato, with co-supervisor Professor Guillaume Lajoie.

My research focuses on amortized ML techniques for applications to Neuroprosthetics, developing efficient methods for neural stimulation optimization in spinal cord injury therapy.

I completed my B.Sc. First-Class Honours in Computer Science with a Minor in Neuroscience at McGill University (GPA: 3.73/4.0). My work spans Gaussian Processes, Large Language Models, Foundation Models, and their applications to healthcare and neuroscience.

Research Interests

Neuroprosthetics

Developing amortized ML techniques and Bayesian optimization methods for neural stimulation in spinal cord injury therapy.

Gaussian Processes

Hierarchical Gaussian Process methods for sample-efficient Bayesian Optimization in high-dimensional spaces.

Large Language Models

Analyzing LLM training dynamics and developing methods to reduce hallucinations for safer AI deployment.

Neuroimaging

Using machine learning to analyze fMRI and TMS data for understanding brain function and task prediction.

Publications

ACL 2025

Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training

S. Mohammadzadeh*, J. D. Guerra*, M. Bonizzato, R. Rabbany, and G. Farnadi

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5538-5554, Vienna, Austria

arXiv 2025

Bidirectional Information Flow (BIF) - A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization

J. D. Guerra, T. Garbay, G. Lajoie, and M. Bonizzato

arXiv:2505.11294, May 2025

Heliyon 2024

Inhibition of the inferior parietal lobe triggers state-dependent network adaptations

K. A. Williams, O. Numssen, J. D. Guerra, J. Kopal, D. Bzdok, and G. Hartwigsen

Heliyon, vol. 10, no. 21, November 2024

Presentations & Talks

Oct 2025

Best Poster Award

UNIQUE Scientific Retreat, Montreal

Jul 2025

Poster Presentation

ACL 2025, Vienna, Austria

Jun 2025

Presenter

Neuroprosthetics Symposium, Université de Montréal

Apr 2025

Selected Oral Presentation

CIRCA Scientific Retreat, Montreal

Mar 2025

Selected Oral Presentation

PolyCongré, Polytechnique Montréal

Mar 2025

Speaker - SNC Neurodiscussions

Université de Montréal

Feb 2025

Workshop Leader - Deep Dive on DeepLabCut

CIRCAteliers, Université de Montréal

Dec 2024

Poster Presentation

Safe Generative AI Workshop @ NeurIPS 2024, Vancouver

Education

Sep 2024 - May 2026

M.ASc in Software Engineering

Polytechnique Montréal & Mila - Quebec AI Institute

GPA: 4.0/4.0

Principal Investigator: Marco Bonizzato | Co-supervisor: Guillaume Lajoie

Research: Amortized ML techniques for applications to Neuroprosthetics

Coursework: 3D Reconstruction of Medical Images, Representation Learning, Continual Machine Learning, Neurotechnology and Neuroscience

Sep 2020 - May 2024

B.Sc. First-Class Honours Computer Science

McGill University

GPA: 3.73/4.0 | Minor in Neuroscience

Coursework: Honours Thesis, Reinforcement Learning, NLP, Responsible AI, Applied ML, Honours Algorithms & Data Structures

Awards & Honors

2021

Quebec Excellence Bursary

For Computer Science

Gouvernement du Québec

Get in Touch

I'm always interested in discussing research collaborations, opportunities, or chatting about AI and neuroscience.

+1 (514) 926-4604
Montreal, Quebec, Canada