<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Marius Henry | Language, Computation and Cognition Lab (LaCoCo)</title><link>https://lacoco-lab.github.io/home/authors/marius-henry/</link><atom:link href="https://lacoco-lab.github.io/home/authors/marius-henry/index.xml" rel="self" type="application/rss+xml"/><description>Marius Henry</description><generator>Wowchemy (https://wowchemy.com)</generator><language>en-us</language><lastBuildDate>Tue, 27 Oct 2026 00:00:00 +0000</lastBuildDate><image><url>https://lacoco-lab.github.io/home/media/icon_hu8f60ba4db9ab46760d26456651b7f58b_9910_512x512_fill_lanczos_center_3.png</url><title>Marius Henry</title><link>https://lacoco-lab.github.io/home/authors/marius-henry/</link></image><item><title>Quantitative Generalization Bounds for Multi-Layer Transformers: A Few Long Strings can Beat Many Short Ones</title><link>https://lacoco-lab.github.io/home/publication/henry2026quantitative/</link><pubDate>Tue, 27 Oct 2026 00:00:00 +0000</pubDate><guid>https://lacoco-lab.github.io/home/publication/henry2026quantitative/</guid><description/></item></channel></rss>