Distinguished Speaker Morteza Mardani - Steering Diffusion Models for Generative AI

#sps #generativeAI
Share

Diffusion models are advancing generative AI across vision, scientific, and natural language domains. As we scale data and compute, foundation models learn rich priors over high-dimensional and multimodal data. This talk focuses on leveraging these priors for solving complex downstream tasks using test-time scaling—with guidance and reinforcement learning—covering practical methods, trade-offs, and examples.


  Date and Time

  Location

  Hosts

  Registration


  • Add_To_Calendar_icon Add Event to Calendar

Loading virtual attendance info...

  • Camino del Molino 5
  • Campus de Fuenlabrada
  • Fuenlabrada, Madrid
  • Spain 28942
  • Building: Edificio de Gestión
  • Room Number: Salón de Actos
  • Click here for Map
  • Contact Event Host
  • Co-sponsored by ELLIS Madrid Unit, Universidad Rey Juan Carlos

  Speakers

Morteza Mardani

Topic:

Steering Diffusion Models for Generative AI

Diffusion models are advancing generative AI across vision, scientific, and natural language domains. As we scale data and compute, foundation models learn rich priors over high-dimensional and multimodal data. This talk focuses on leveraging these priors for solving complex downstream tasks using test-time scaling—with guidance and reinforcement learning—covering practical methods, trade-offs, and examples.

Biography:

Morteza Mardani is a Principal Scientist at NVIDIA Research, where he is responsible for generative AI algorithms. He is also a visiting researcher in the Department of Electrical Engineering at Stanford University and serves as a Distinguished Industry Speaker for the IEEE Signal Processing Society. Previously, he worked as a postdoctoral researcher and research associate at Stanford between 2015 and 2020, and was a visiting researcher at the RISE Lab at UC Berkeley in 2015. He earned his PhD in Electrical Engineering from the University of Minnesota. His contributions to generative and statistical learning have been recognized with several awards, including the IEEE Signal Processing Society’s Young Author Best Paper Award in 2017.