Skip to content
InfratoApp

NVIDIA · Course

Building AI Agents with Multimodal Models (instructor-led)

Building AI Agents with Multimodal Models is an instructor-led NVIDIA workshop on neural-network models that understand many kinds of data, covering fusion techniques, PDF extraction with OCR and agent orchestration.

Open at NVIDIA ↗Common questions

Who it suits

  • Developers working with several data types, such as images, lidar or documents.
  • Engineers who want to extend language models to non-language input.

What it covers

  • Making different data types neural-network ready.
  • Early, late and intermediate model fusion.
  • PDF extraction using OCR, and the difference between modality and agent orchestration.
  • Customising NVIDIA AI Blueprints with Video Search and Summarization.

Common questions about Building AI Agents with Multimodal Models (instructor-led)

How does it start?
With a robotics use case showing how data types shape an effective architecture, then applies the ideas to language models.
How is it taught?
As an instructor-led workshop; NVIDIA says to work with the instructor on timing for your session.
What does it cost?
NVIDIA lists instructor-led workshops as contact-us for pricing and dates, so check its page; they change.

More like this

Keep learning on Infrato

Where this comes from

Written from NVIDIA’s own pages, read on 2026-10-14. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with NVIDIA and this is not an endorsement.