Borja Balle is a researcher focused on machine learning theory, algorithms, applications and privacy-preserving data analysis.
How media typically covers Borja Balle
Borja Balle as author
Scaling laws for differentially private language model training accurately model compute-privacy-utility tradeoffs and identify optimal training configurations for privacy-preserving LLM development.
“Author of "Tool-space interference in the MCP era: Designing for agent compatibility at sca" on arXiv”