<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Blog on Abhiraj Bibhar</title><link>https://abhiraj.pages.dev/blog/</link><description>Recent content in Blog on Abhiraj Bibhar</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 18 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://abhiraj.pages.dev/blog/index.xml" rel="self" type="application/rss+xml"/><item><title>Why Federated Learning Is Harder Than the Tutorials Make It Look</title><link>https://abhiraj.pages.dev/blog/federated-learning-harder-than-tutorials/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://abhiraj.pages.dev/blog/federated-learning-harder-than-tutorials/</guid><description>The gap between a federated averaging demo notebook and a system that survives real hospitals, spotty networks, and adversarial clients is bigger than most tutorials let on.</description></item><item><title>What I Changed After a Decade of Teaching Algorithms</title><link>https://abhiraj.pages.dev/blog/decade-of-teaching-algorithms/</link><pubDate>Mon, 02 Mar 2026 00:00:00 +0000</pubDate><guid>https://abhiraj.pages.dev/blog/decade-of-teaching-algorithms/</guid><description>Ten years of CS 210 taught me that the biggest predictor of student success isn&amp;rsquo;t talent — it&amp;rsquo;s how quickly wrong mental models get corrected.</description></item><item><title>Explainability Is Not a Feature You Bolt On Afterward</title><link>https://abhiraj.pages.dev/blog/explainability-not-bolted-on/</link><pubDate>Wed, 14 Jan 2026 00:00:00 +0000</pubDate><guid>https://abhiraj.pages.dev/blog/explainability-not-bolted-on/</guid><description>Post-hoc explanation methods are useful, but treating explainability as a wrapper around an already-trained black box quietly limits what kinds of trust you can actually earn.</description></item></channel></rss>