BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Madrid BEGIN:DAYLIGHT DTSTART:20260329T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20251026T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260202T175721Z UID:54088D69-F4EC-4E8D-AE46-7C569CE7E602 DTSTART;TZID=Europe/Madrid:20260119T110000 DTEND;TZID=Europe/Madrid:20260119T120000 DESCRIPTION:Diffusion models are advancing generative AI across vision\, sc ientific\, and natural language domains. As we scale data and compute\, fo undation models learn rich priors over high-dimensional and multimodal dat a. This talk focuses on leveraging these priors for solving complex downst ream tasks using test-time scaling—with guidance and reinforcement learn ing—covering practical methods\, trade-offs\, and examples.\n\nCo-sponso red by: ELLIS Madrid Unit\, Universidad Rey Juan Carlos\n\nSpeaker(s): Mor teza Mardani\n\nRoom: Salón de Actos\, Bldg: Edificio de Gestión\, Camin o del Molino 5\, Campus de Fuenlabrada\, Fuenlabrada\, Madrid\, Spain\, 28 942\, Virtual: https://events.vtools.ieee.org/m/532965 LOCATION:Room: Salón de Actos\, Bldg: Edificio de Gestión\, Camino del Mo lino 5\, Campus de Fuenlabrada\, Fuenlabrada\, Madrid\, Spain\, 28942\, Vi rtual: https://events.vtools.ieee.org/m/532965 ORGANIZER:javierp@usal.es SEQUENCE:20 SUMMARY:Distinguished Speaker Morteza Mardani - Steering Diffusion Models f or Generative AI URL;VALUE=URI:https://events.vtools.ieee.org/m/532965 X-ALT-DESC:Description: <br /><p class="MsoNormal"><span lang="EN-GB">Diffu sion models are advancing generative AI across vision\, scientific\, and n atural language domains. As we scale data and compute\, foundation models learn rich priors over high-dimensional and multimodal data. This talk foc uses on leveraging these priors for solving complex downstream tasks using test-time scaling&mdash\;with guidance and reinforcement learning&mdash\; covering practical methods\, trade-offs\, and examples.</span></p> END:VEVENT END:VCALENDAR