<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en"><generator uri="https://jekyllrb.com/" version="3.10.0">Jekyll</generator><link href="https://parsaghazvinian.com/feed.xml" rel="self" type="application/atom+xml" /><link href="https://parsaghazvinian.com/" rel="alternate" type="text/html" hreflang="en" /><updated>2026-11-18T21:21:00-05:00</updated><id>https://parsaghazvinian.com/feed.xml</id><title type="html">Parsa Ghazvinian</title><subtitle>Parsa Ghazvinian is a Ph.D. candidate in Computer Science at Georgia State University working on efficient and trustworthy AI: parameter-efficient fine-tuning, how visual-token pruning in vision-language models is evaluated, the reliability of LLM systems, and encrypted inference.</subtitle><author><name>Parsa Ghazvinian</name></author></feed>