Pietro Lesci's picture

Pietro Lesci

pietrolesci

AI & ML interests

I like developing and applying causal methods to study the effect of training choices on models’ behaviour, including memorisation, shortcut learning, and tokenisation.

Organizations

MilaNLP's profile picture EleutherAI's profile picture Social Post Explorers's profile picture Hugging Face Discord Community's profile picture Training Dynamics's profile picture Unlearning's profile picture ByteSpan Tokenisers's profile picture co-evolve's profile picture Tiny Labs's profile picture LangMAP's profile picture