← Search

Avishai Elmakies

2 accepted papers

2025

Slamming: Training a Speech Language Model on One GPU in a Day

ACL 2025finding

We introduce *Slam*, a recipe for training high-quality Speech Language Models (SLMs) on a single academic GPU in 24 hours. We do so through empirical analysis of model initialisation and architecture, synthetic training data, preference optimisation with synthetic data and tweaking all other compon…