Dongxi 东锡 NLP· @dongxi_nlp · X·· 4 小时前AI 评分38
AI 导读
如何训练一个 SOTA 基础决策模型？ Drex 技术报告给出了完整配方： 核心是 SFT + RLAF + 多模态训练流程 - SFT 利用标注数据和教师生成数据构建基础决策能力 - RLAF 通过带 KL 正则化的调整反馈来优化决策概率 - 通过视觉微调实现多模态支持 Drex Max 在 Decision Bench v4 上达到 94.0% 准确率，展现出接近 SOTA 的结构化决策能力，同时具备较低的推理延迟。 推荐阅读！
正文 · 原文
如何训练一个 SOTA Foundation Decision Model?
Drex Technical Report 给出了完整 recipe:
核心是 SFT + RLAF + multimodal training pipeline
- SFT builds foundational decision-making capabilities using labeled and teacher-generated data
- RLAF refines decision probabilities using adjusted feedback with KL regularization
- Multimodal support through vision fine-tuning
Drex Max 在 Decision Bench v4 上达到 94.0% accuracy，展现出接近 SOTA 的结构化决策能力，同时具备较低的 inference latency。
推荐阅读！
How are Decision Models Trained? Today, we are publishing the Drex Technical Report for the developer community! 🚀 Discover details on how the State-of-the-art Open-Source decision models are trained with RLAF. Build more at: https://console.nace.ai/ (try for free) P.S. Drex Max 1.1 and Drex for Finance are closed sourced and designed for enterprise use-cases在 X 查看被引用的帖子
来源：Dongxi 东锡 NLP · x.com