<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Distillation on Damien Riquet</title><link>https://driquet.info/tags/distillation/</link><description>Recent content in Distillation on Damien Riquet</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Damien Riquet</copyright><lastBuildDate>Sat, 21 Nov 2026 14:48:13 +0100</lastBuildDate><atom:link href="https://driquet.info/tags/distillation/index.xml" rel="self" type="application/rss+xml"/><item><title>No Labels? Borrow Them: Distilling a Classifier Locally</title><link>https://driquet.info/distilling-a-classifier/</link><pubDate>Sat, 21 Nov 2026 10:00:00 +0100</pubDate><guid>https://driquet.info/distilling-a-classifier/</guid><description> Rent a teacher for a few cents, keep a 150M student. How much of the teacher survives, and what does it cost? In the previous post, the two ladders (decision models and fine-tuned encoders) left a gap in the middle. A decision model needs no labels, but it is slow: on CLINC, …</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/distilling-a-classifier/featured.webp"/></item></channel></rss>