<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Inverse Design on Sibasankar Panigrahy</title><link>https://siba-p.github.io/tags/inverse-design/</link><description>Recent content in Inverse Design on Sibasankar Panigrahy</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 09 Oct 2026 07:00:00 +0530</lastBuildDate><atom:link href="https://siba-p.github.io/tags/inverse-design/index.xml" rel="self" type="application/rss+xml"/><item><title>Teaching attention to read a surface</title><link>https://siba-p.github.io/notebook/2026-10-09-attention-reads-a-surface/</link><pubDate>Fri, 09 Oct 2026 07:00:00 +0530</pubDate><guid>https://siba-p.github.io/notebook/2026-10-09-attention-reads-a-surface/</guid><description>&lt;p&gt;Umbrella sampling is the workhorse for computing how strongly a polymer sticks to a surface. You pull the chain away in windows, sample each one, and stitch them together into a potential of mean force (PMF). It is reliable, and it is slow. If you want to &lt;em&gt;screen&lt;/em&gt; polymer sequences against surface patterns, the combinatorics quickly outrun any compute budget.&lt;/p&gt;</description></item></channel></rss>