<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI模型与架构 on AI 早报</title><link>https://ai-news.example.com/categories/ai%E6%A8%A1%E5%9E%8B%E4%B8%8E%E6%9E%B6%E6%9E%84/</link><description>Recent content in AI模型与架构 on AI 早报</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Tue, 07 Jul 2026 09:50:18 +0800</lastBuildDate><atom:link href="https://ai-news.example.com/categories/ai%E6%A8%A1%E5%9E%8B%E4%B8%8E%E6%9E%B6%E6%9E%84/feed.xml" rel="self" type="application/rss+xml"/><item><title>[EN] Cappy：用小模型评分器超越和提升大型多任务语言模型</title><link>https://ai-news.example.com/articles/en-cappy/</link><pubDate>Tue, 07 Jul 2026 09:50:18 +0800</pubDate><guid>https://ai-news.example.com/articles/en-cappy/</guid><description>Google Research 提出轻量级预训练评分器 Cappy（基于 RoBERTa，仅 3.6 亿参数），通过为指令与候选响应生成正确性分数，可独立完成分类任务或作为辅助组件提升大型多任务语言模型性能，无需微调或反向传播，显著降低存储和计算需求，并兼容闭源模型。</description></item></channel></rss>