<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Inference-Scaling on 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/inference-scaling/</link><description>Recent content in Inference-Scaling on 兜忆轩 | Cedric's Compiler Notes</description><image><title>兜忆轩 | Cedric's Compiler Notes</title><url>https://douyixuan.github.io/images/papermod-cover.png</url><link>https://douyixuan.github.io/images/papermod-cover.png</link></image><generator>Hugo -- 0.146.0</generator><language>en-us</language><lastBuildDate>Tue, 15 Sep 2026 12:00:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/inference-scaling/index.xml" rel="self" type="application/rss+xml"/><item><title>002 · HLS-Eval：十次尝试拿到满分，意味着 AI 会设计硬件了吗？</title><link>https://douyixuan.github.io/posts/ai-silicon-papers/2026-09-15/</link><pubDate>Tue, 15 Sep 2026 12:00:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-silicon-papers/2026-09-15/</guid><description>读 HLS-Eval 的 Agent 评测论文：区分一次成功与多次采样成功，追问测试通过、可综合与硬件设计能力之间的距离。</description></item></channel></rss>