<!DOCTYPE html>
<html>
  <head>

    <meta http-equiv="content-type" content="text/html; charset=UTF-8">
  </head>
  <body>
    <p>Dear colleagues,<br>
      <br>
      We cordially invite you to submit your paper to the Special
      Session: <br>
      "<b>Generative Foundation Models for Robotics: From Language and
        Vision to Embodied<br>
        Action</b>", to be held at the <b>2026 IEEE World Congress on
        Computational<br>
        Intelligence (WCCI 2026)</b>.<br>
      <br>
      <b>Website</b>: <a class="moz-txt-link-freetext"
        href="https://wccigenai2026.github.io">https://wccigenai2026.github.io</a><br>
      <br>
      This special session aims to bring together recent advances in
      generative<br>
      and foundation models and their applications to robotics. Topics
      of<br>
      interest include, but are not limited to:</p>
    <ul>
      <li>Diffusion models for robot trajectory planning and control</li>
      <li> Generative adversarial networks for robotic applications</li>
      <li> Flow matching methods for robotic control</li>
      <li> Language-guided robot manipulation and navigation</li>
      <li><span style="white-space: pre-wrap">Meta-learning for adaptive robotic behaviors</span></li>
      <li><span style="white-space: pre-wrap"></span><span
        style="white-space: pre-wrap">Multi-task planning and execution</span></li>
      <li><span style="white-space: pre-wrap"></span><span
        style="white-space: pre-wrap">Transfer learning across robotic domains and environments</span></li>
      <li><span style="white-space: pre-wrap"></span><span
        style="white-space: pre-wrap">Generative imitation learning from human demonstrations</span></li>
      <li><span style="white-space: pre-wrap"></span><span
        style="white-space: pre-wrap">Generative design of robot morphologies</span></li>
      <li><span style="white-space: pre-wrap"></span><span
        style="white-space: pre-wrap">Co-evolution of robot structure and control</span></li>
      <li><span style="white-space: pre-wrap"></span><span
        style="white-space: pre-wrap">Curriculum learning with generative models</span></li>
      <li><span style="white-space: pre-wrap"></span><span
        style="white-space: pre-wrap">Constraint-aware generative planning</span></li>
    </ul>
    <p><b>Organizers:</b><br>
      Erdal Kayacan (Paderborn University, Germany)<br>
      Chen Qinyu (Leiden University, The Netherlands)<br>
      Konstantinos Alexis (Norwegian University of Science and
      Technology, Norway)<br>
      Guido de Croon (TU Delft, The Netherlands)<br>
      Erdi Sayar (Paderborn University, Germany)<br>
      Van Huyen Dang (Paderborn University, Germany)<br>
      Alper Yegenoglu (Paderborn University, Germany)<br>
      Adrian Redder (Paderborn University, Germany)</p>
    <p><b>Paper Submission Deadline</b>: 31 January, 2026 (UTC-12)</p>
    <p>Kind regards,<br>
      Alper</p>
    <p>--</p>
    <div class="moz-signature"> Dr. <br>
      <strong style="font-size: 1.125em">Alper Yegenoglu</strong><br>
      Postdoctoral Researcher<br>
      Automatic Control Group (RAT)<br>
      University of Paderborn<br>
      Warburger Str. 100<br>
      33098 Paderborn<br>
      Germany<br>
      <strong>Office</strong> P1.7.15.4<br>
      <strong>Telephone</strong> +49 5251 60-1898<br>
      <strong>E-Mail</strong> <a
        href="mailto:alper.yegenoglu@uni-paderborn.de"
        class="moz-txt-link-freetext">alper.yegenoglu@uni-paderborn.de</a><br>
      <strong>Web</strong> <a href="https://en.ei.uni-paderborn.de/rat"
        target="_blank" class="moz-txt-link-freetext">
        https://en.ei.uni-paderborn.de/rat</a> </div>
    <p><br>
    </p>
  </body>
</html>