Training Foundation Models with a Single Algorithm

Paper recorded by Signals 4 on 2026-10-29 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-29 on arXiv · recorded by Signals 4 on 2026-10-30

Category: cs.LG · 机器学习 · first seen 2026-10-30

Abstract

Foundation models are typically trained in stages: pretraining, midtraining, supervised fine-tuning (SFT), and reinforcement learning (RL), with changes in both data and learning algorithms. We show that this algorithmic separation is not fundamental. By deriving suitable RL objectives as maximum-likelihood fitting to model-generated target distributions, we place all of these stages under a singl

Read on arXiv →