Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
Pietro Lesci's picture
15 4 9

Pietro Lesci

pietrolesci
yjernite's profile picture Guoh34's profile picture alirahmati's profile picture
·
https://pietrolesci.github.io/
  • pietro_lesci
  • pietrolesci
  • pietrolesci
  • pietrolesci.bsky.social

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

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

authored a paper 8 months ago

PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs

Paper • 2503.09543 • Published Mar 12
authored a paper 9 months ago

Self-Training Large Language Models for Tool-Use Without Demonstrations

Paper • 2502.05867 • Published Feb 9
authored a paper about 1 year ago

Tending Towards Stability: Convergence Challenges in Small Language Models

Paper • 2410.11451 • Published Oct 15, 2024
authored 2 papers over 1 year ago

Causal Estimation of Memorisation Profiles

Paper • 2406.04327 • Published Jun 6, 2024 • 1

AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasets

Paper • 2404.05623 • Published Apr 8, 2024 • 3
authored a paper about 2 years ago

Diable: Efficient Dialogue State Tracking as Operations on Tables

Paper • 2305.17020 • Published May 26, 2023
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs