About
I am an Argentinian physicist currently working on understanding how semantic and syntactic information is encoded in large language models. More broadly, I’m interested in machine learning, its connection to Wilsonian renormalization group theory, and the geometry of representations, whether learned by biological or silicon-based networks.
Semantics in LLMs
- A quantitative analysis of semantic information in deep representations of text and images arXiv
- Differential syntactic and semantic encoding in LLMs arXiv (Accepted for ICML 2026)
Binary Intrinsic Dimension (BID)
- Unsupervised detection of semantic correlations in big data Nature Communications Physics
- Family-Vicsek universality of the binary intrinsic dimension of nonequilibrium data Physical Review E Letter
- The dimensionality of the Hopfield model arXiv