// model_card
marcel-mateos-salles
The static, printable readout of the interactive network at marcelmatsal.com.
--- model: marcel-mateos-salles architecture: 9-layer experience stack · 2 probe-able unit layers base_model: brown-university/cs-econ (magna cum laude, honors) finetuned_for: [backend engineering, ML research, interpretability] release: v2026.05 license: open-to-opportunities-1.0 contact: marcel_mateos_salles@alumni.brown.edu ---
Model description
Backend software engineer and ML researcher. Recent graduate of Brown University (Computer Science-Economics), member of the GalilAI Group with Prof. Randall Balestriero, and incoming Software Engineer at Pinterest. Research interests: LLMs, model interpretability, and self-supervised learning — with a particular focus on spurious correlations under parameter-efficient finetuning.
Architecture
One unit per role, stacked in temporal order. t-0 is the most recent layer; activations reflect how central each unit is to the current model.
| layer | unit | source | period | act |
|---|---|---|---|---|
| t-0 | Pinterest SWE | Incoming July 2026 | 0.78 | |
| t-1 | Head TA · CL | CSCI1460: Computational Linguistics | Dec 2025 - May 2026 | 0.60 |
| t-2 | Pinterest Intern | Summer 2025 | 0.74 | |
| t-3 | TA · Deep Learning | CSCI 1470: Deep Learning | Dec 2024 - May 2025 | 0.62 |
| t-4 | GalilAI Research | GalilAI Group @ Brown University | Oct 2024 - Present | 0.96 |
| t-5 | Dexcom Intern | Dexcom | Jun 2024 - Aug 2024 | 0.70 |
| t-6 | TA · Big Data | Econ 1000: Using Big Data to Solve Social and Economic Problems | Sep 2023 - Dec 2023 | 0.55 |
| t-7 | SAVE Lab | SAVE Lab @ UTSA | May 2023 - Sep 2023 | 0.82 |
| t-8 | Brown · CS-Econ | Brown University | Sep 2022 - May 2026 | 0.90 |
Training data
- Brown University — B.S. Computer Science–Economics, Magna Cum Laude, Honors. GPA 4.0/4.0.
- Reinforced by teaching: Deep Learning (CSCI 1470), Computational Linguistics (CSCI 1460, Head TA), and Using Big Data to Solve Social and Economic Problems (Econ 1000).
- Fine-tuned in production at Pinterest (GenAI tooling, observability) and Dexcom (mobile architecture).
Evaluation
LoRA Users Beware: A Few Spurious Tokens Can Manipulate Your Finetuned Model
Marcel Mateos Salles, Praney Goyal, Pradyut Sekhsaria, Hai Huang, Randall Balestriero
NeurIPS 2025 workshop · poster · ICLR 2026 workshop · oral · arXiv
When Efficiency Enables Shortcuts: Studying Spurious Correlations Under LoRA Finetuning
Marcel Mateos Salles
Brown University honors thesis · thesis · PDF
Feature dictionary
Intended use
Backend systems and ML research teams that want an engineer who reads the papers and ships the infrastructure. Direct use: marcel_mateos_salles@alumni.brown.edu. See also GitHub, Google Scholar, LinkedIn, and the resume (PDF).
Limitations
- Performance degrades measurably when the coffee supply is ablated.
- Addicted to fitness and spending time outside. Currently training for the Seawheeze Halfmarathon.
- Will occasionally overfit to a random fixation.
Citation
@misc{mateossalles2026,
author = {Mateos Salles, Marcel},
title = {marcel-mateos-salles: an interpretable portfolio},
year = {2026},
url = {https://www.marcelmatsal.com}
}// generated from the same data that powers the network