I study how meaning is represented in language models and in the human brain.
I’m a Ph.D. student at the Max Planck Institute for Software Systems (MPI-SWS) in the Bridging AI and Neuroscience (BrAIN) group, advised by Dr. Mariya Toneva and co-advised by Dr. Krishna P. Gummadi.
My research sits at the intersection of machine learning and neuroscience. I use LLMs to build interpretable, cognitively grounded representations of context-dependent meaning, and use them to study how the brain processes language. More broadly, I’m interested in two directions: using the brain to inspire better machine learning systems, and using machine learning to understand the brain.
Background
- Master’s in Computer Science, PUCRS, Brazil (2022): mitigating biases in facial analysis systems. Advised by Dr. Soraia Musse and co-advised by Dr. Adriano Veloso (UFMG).
- Research internships: Google Brain, Warsaw (multi-modal models for zero-shot VQA) and MPI-SWS, Saarbrücken (robustness to adversarial attacks).
- ML engineer at Kunumi: ML for Intensive Care Units and NLP for a conversational assistant.
- B.Sc. in Computer Engineering, PUCRS, Brazil (2019). Engineer of the Year Award by SERGS and Student Highlight Award by the Brazilian Computer Society (SBC), both in 2019.
Beyond research: I occasionally write A Curious Brain on Substack, about minds, AI, and staying mentally sharp in the age of AI. Outside the lab, I'm a runner (and a former competitive swimmer in Brazil), and I love reading books about AI and the brain.
News
- October 2026: New preprint! SCRIBE: Scalable Contextual Representations of Interpretable Brain-Grounded Semantics: we use LLMs to annotate context-dependent meaning along human-interpretable semantic dimensions, at scale.
- October 2026: Co-organizing and TA-ing the seminar Foundation Models of the Human Mind at Saarland University.
- September 2026: Decomposing Brain-LLM Alignment with Interpretable Semantic Representations accepted at the NeurIPS 2026 Workshop on Foundation Models for the Brain and Body. 🎉
- September 2026: Selected as one of 200 young researchers for the 13th Heidelberg Laureate Forum, where I presented a poster (one of 30 selected projects) on modeling context-dependent meaning in the brain with LLMs. 🎉
- September 2025: Large Language Models as Model Organisms for Human Associative Learning accepted at NeurIPS 2025 (presented in San Diego, December 2025). 🎉
- July 2025: Attended the NeuroAI Course in Lisbon, funded by the Boehringer Ingelheim Fonds.
- May 2025: Non-Monotonic Plasticity in Large Language Models accepted at CCN 2025 (presented in Amsterdam, August 2025). 🎉
- May 2025: Investigating the Effects of Fairness Interventions Using Pointwise Representational Similarity accepted in TMLR. 🎉
- September 2024: Passed my Qualifying Exam.
- May 2023: Started my Ph.D. at MPI-SWS.
- December 2022: Joined MPI-SWS as a research assistant.
- July–December 2022: Second research internship at MPI-SWS.
- July 2022: Graduated from my Master’s in Computer Science! 🎓
- November 2021–February 2022: First research internship at MPI-SWS.
- August–November 2021: Research internship at Google Brain in Warsaw.
- December 2019: Graduated from my Bachelor’s in Computer Engineering! 🎓