Events

EAG London 2026 was an event about effective altruism, AI safety, and related topics.

The Workshop on Securing AI Research in Latin America was a 3-day workshop held in Santiago, Chile, from May 12 to 14, 2026, and organized by Deloitte in partnership with the U.S. Department of State.

ICLR is the International Conference on Learning Representations. In this edition, held in Rio de Janeiro, I will present two papers: Cooperative Sheaf Neural Networks and Orthogonal Gradient Projection for Continual LLM Unlearning.

PROPOR 2026 is the International Conference on Computational Processing of Portuguese. In this edition, held in Salvador, I will present a poster about my work done on Math-PT.

AISB is a 4-week long intensive program to bring researchers and engineers up to speed on security fundamentals for AI systems. During this program, I developed a replication of the watermark stealing attack.

EAG London 2025 was an event about effective altruism, AI safety, and related topics.

ML4Good is a bootcamp focused on AI Safety upskilling, including workshops on interpretability, alignment and governance of artificial intelligence. In this edition, I participated as a teaching assistant.

CNMAC is a Brazilian conference on applied mathematics, where I presented a poster about Graph Neural Networks titled “SRGNN: Simple Recurrent GNN”.

ML4Good is a bootcamp focused on AI Safety upskilling, including workshops on interpretability, alignment and governance of artificial intelligence. In this edition, I developed a Mechanistic Interpretability Course.

EAGxLATAM is an effective altruism event in Mexico City about existential risks, AI safety and the animal cause. There, I could talk with a lot of people that works with AI safety (e.g.: students from the AI Futures Fellowship, researchers from groups like FAR AI, etc.) and watch lectures about relevant topics.