Benjamin Therien's picture

5

Benjamin Therien

btherien

·

https://bentherien.github.io/

AI & ML interests

Passionate about machine learning research! Currently working on efficient foundation model pre-training and learned optimization.

Organizations

authored 3 papers over 1 year ago

Continual Pre-Training of Large Language Models: How to (re)warm your model?

Paper • 2308.04014 • Published Aug 8, 2023 • 2

$μ$LO: Compute-Efficient Meta-Generalization of Learned Optimizers

Paper • 2406.00153 • Published May 31, 2024 • 13

Simple and Scalable Strategies to Continually Pre-train Large Language Models

Paper • 2403.08763 • Published Mar 13, 2024 • 51