统一训练框架：把预训练到 RL 整合进单一算法
Training Foundation Models with a Single Algorithm
一篇把 SFT 和 RL 说成同一件事的论文，训练管线能简化成数据配比问题，做模型训练的人可以看看思路。
一篇 arXiv 论文提出 unified training，把预训练、midtraining、SFT、RL 四个阶段统一到同一个基于似然的训练算法中。作者将 RL 目标推导为对模型生成目标分布的最大似然拟合，从而把训练生命周期简化为选择数据、比例和时机的组合问题。配套实现将静态数据与 RL 生成混在同一 trainer 中，实验显示在精度-算力权衡和任务覆盖上均有提升，并为持续学习提供更强起点。
Training Foundation Models with a Single Algorithm
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 single likelihood-based training algorithm, unified training. This perspective turns the foundation-model training lifecycle into a problem of choosing which data to train on, in what proportions, and when, with conventional staged training as a special case. We instantiate this framework in a unified training system that mixes static data and RL generations within a single trainer. Across controlled and real-world experiments, unified training improves the accuracy-compute tradeoff and task coverage while preserving broader capabilities, and provides a stronger starting point for continual learning. This work lays the groundwork for a unified science of foundation-model training, connecting mathematical principles, training infrastructure, and the development of model capabilities.