Human Attention for Large Language Model Training
Bachelor’s thesis developed with Telefónica I+D and UPC, awarded 10/10 and proposed for honours.
Research index / 2026
Research
Research on geometric deep learning, efficient graph representations, and interpretable language models with gaze.
→
Fewer Edges, Faster Protein Graph Learning
A first-author GRaM @ ICLR 2026 blogpost on sparse protein graphs and efficient geometric message passing.
The archive includes accepted research writing, thesis work, and ongoing investigations.