<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>Mario Gemoll</title>
  <link href="https://mariogemoll.com/"/>
  <link href="https://mariogemoll.com/atom.xml" rel="self"/>
  <updated>2026-07-17T15:53:35.632Z</updated>
  <id>https://mariogemoll.com/</id>
  <author>
    <name>Mario Gemoll</name>
  </author>
  <entry>
    <title>Pick and Place with the SO-101 Robot Arm</title>
    <link href="https://mariogemoll.com/pick-and-place"/>
    <id>https://mariogemoll.com/pick-and-place</id>
    <published>2026-07-17T15:00:00.000Z</published>
    <updated>2026-07-17T15:00:00.000Z</updated>
    <summary>An end-to-end robotics project covering inverse kinematics, motion planning, computer vision, sim-to-real transfer, and ACT imitation learning.</summary>
  </entry>
  <entry>
    <title>LLM Posttraining</title>
    <link href="https://mariogemoll.com/llm-posttraining"/>
    <id>https://mariogemoll.com/llm-posttraining</id>
    <published>2026-04-10T15:00:00.000Z</published>
    <updated>2026-04-10T15:00:00.000Z</updated>
    <summary>A guide to LLM posttraining basics: LoRA, SFT, RLHF, RLVR.</summary>
  </entry>
  <entry>
    <title>Reinforcement Learning</title>
    <link href="https://mariogemoll.com/reinforcement-learning"/>
    <id>https://mariogemoll.com/reinforcement-learning</id>
    <published>2026-02-10T14:30:00.000Z</published>
    <updated>2026-03-25T10:00:00.000Z</updated>
    <summary>Foundations of reinforcement learning, from Markov decision processes and value functions to dynamic programming, Monte Carlo methods, temporal-difference learning, and policy gradients.</summary>
  </entry>
  <entry>
    <title>Diffusion</title>
    <link href="https://mariogemoll.com/diffusion"/>
    <id>https://mariogemoll.com/diffusion</id>
    <published>2026-01-14T22:00:00.000Z</published>
    <updated>2026-01-14T22:00:00.000Z</updated>
    <summary>Extending the flow matching framework to diffusion models.</summary>
  </entry>
  <entry>
    <title>Flow Matching</title>
    <link href="https://mariogemoll.com/flow-matching"/>
    <id>https://mariogemoll.com/flow-matching</id>
    <published>2025-11-25T10:00:00.000Z</published>
    <updated>2026-01-14T21:00:00.000Z</updated>
    <summary>An overview of flow matching techniques for generative modeling.</summary>
  </entry>
  <entry>
    <title>Attention Is All You Need</title>
    <link href="https://mariogemoll.com/attention-is-all-you-need"/>
    <id>https://mariogemoll.com/attention-is-all-you-need</id>
    <published>2025-11-07T16:00:00.000Z</published>
    <updated>2025-11-07T16:00:00.000Z</updated>
    <summary>Describing the training of an encoder-decoder transformer, following the "Attention Is All You Need" paper.</summary>
  </entry>
  <entry>
    <title>Parallel Corpus Viewer</title>
    <link href="https://mariogemoll.com/parallel-corpus-viewer"/>
    <id>https://mariogemoll.com/parallel-corpus-viewer</id>
    <published>2025-11-07T15:00:00.000Z</published>
    <updated>2025-11-07T15:00:00.000Z</updated>
    <summary>A viewer for the datasets used to train the model for the Attention Is All You Need page.</summary>
  </entry>
  <entry>
    <title>Normalizing Flows</title>
    <link href="https://mariogemoll.com/normalizing-flows"/>
    <id>https://mariogemoll.com/normalizing-flows</id>
    <published>2025-10-28T00:00:00.000Z</published>
    <updated>2025-10-28T00:00:00.000Z</updated>
    <summary>A page exploring the basics of normalizing flows.</summary>
  </entry>
  <entry>
    <title>Variational Autoencoders</title>
    <link href="https://mariogemoll.com/vae"/>
    <id>https://mariogemoll.com/vae</id>
    <published>2025-10-15T00:00:00.000Z</published>
    <updated>2025-10-15T00:00:00.000Z</updated>
    <summary>An interactive exploration of Variational Autoencoders (VAEs) with theory, implementation details, and live demonstrations using a synthetic dataset.</summary>
  </entry>
</feed>