Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
OPEN-1B: A Fully Auditable Training Run
John Donaghy, Brian Wilcox, Oğuzhan Ersoy +6
Open-source language models have a reproducibility problem. Despite releasing weights, training data, and recipes, none of them are provably reproducible due to the non-associativi…
cs.LG2025
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
Jeffrey Amico, Gabriel Passamani Andrade, John Donaghy +12
Post-training language models (LMs) with reinforcement learning (RL) can enhance their complex reasoning capabilities without supervised fine-tuning, as demonstrated by DeepSeek-R1…