<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>about on Cristóbal Alcázar</title>
    <link>https://www.alkzar.cl/tags/about/</link>
    <description>Recent content in about on Cristóbal Alcázar</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-US</language>
    <lastBuildDate>Sun, 02 Oct 2016 22:55:05 -0400</lastBuildDate><atom:link href="https://www.alkzar.cl/tags/about/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>About</title>
      <link>https://www.alkzar.cl/about/</link>
      <pubDate>Sun, 02 Oct 2016 22:55:05 -0400</pubDate>
      
      <guid>https://www.alkzar.cl/about/</guid>
      <description>Hi, I&amp;rsquo;m Cristóbal! MSc in Data Science at Universidad de Chile.
My interests lie in diffusion models and how to adapt them. Specifically, I&amp;rsquo;m interested in using reinforcement learning to build agents on top of pretrained models and gain control over them to (i) expand their generative capabilities, (ii) add specialization through reward functions (RLHF), and (iii) implement exploration mechanisms for control and potential mitigation of mode collapse. I believe that mastering these areas could lead to powerful abstractions in human-computer interaction, enhancing applications and products such as cinematics, games, and scientific tools.</description>
    </item>
    
  </channel>
</rss>
