<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Translations on Cohomology Zero</title><link>https://jen1995.github.io/tags/translations/</link><description>Recent content in Translations on Cohomology Zero</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Fri, 24 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://jen1995.github.io/tags/translations/index.xml" rel="self" type="application/rss+xml"/><item><title>Transformers from Scratch</title><link>https://jen1995.github.io/posts/transformers/</link><pubDate>Fri, 24 Jul 2026 00:00:00 +0000</pubDate><guid>https://jen1995.github.io/posts/transformers/</guid><description>The full series in one post: why attention replaced recurrence; every building block of the Transformer — intuition, formula, PyTorch code, a numpy reference and an honest FLOPs count; then the assembled model, trained on a toy task, with the memory costs and the KV-cache explained.</description></item><item><title>Variational Autoencoder (VAE)</title><link>https://jen1995.github.io/posts/vae/</link><pubDate>Fri, 24 Jul 2026 00:00:00 +0000</pubDate><guid>https://jen1995.github.io/posts/vae/</guid><description>A deep dive into variational autoencoders: the ELBO and its derivation, the reparameterization trick, CVAE — and the discrete-latent line of work (VQ-VAE, VQ-VAE-2, DALL-E) that grew out of it. With self-check questions and a hands-on notebook.</description></item></channel></rss>