Event box

One AI to Rule Them All: How to Build a Large Multimodal Model (LMM) that Handles Text, Images, and Music - Data Hub Tech Talk

Note: the session will be recorded for registrants who cannot attend at the scheduled time.

Modern transformer architectures are adept at not only understanding text, but also images, video, speech, music, and much more. We discuss how these multimodal models work under the hood, and will build and train a simple model that uses multiple input encoders and a shared semantic embedding space. Our model will learn how to jointly interpret text, images, and music.

Date:: Friday, December 6, 2024
Time:: 12:30pm - 1:30pm
Location:: Data Hub presentation / collaboration space
Campus:: University of Idaho - Moscow campus
Presenter:: Dr. Lucas Sheneman, Director - Research Computing and Data Services
Categories:: Data Hub Library Workshop

* Required Field

E-mail

Full Name *

Email *

Status

Undergraduate student

Graduate student

Staff

Faculty

Community

Would you like to receive a recording of this Talk?

Yes

Affiliation / Department (optional):

Questions, comments, or special needs? (Your questions will be routed to the workshop coordinator)

Registration is required. There are 17 in-person seats available. There are 42 online seats available.

Registration Type

In-Person Registration

Online Registration

Upcoming Workshops

Time Zone: Pacific Time - US & Canada (change)

Dec

Make it @ the MILL Graduation Cap Decorating

12:30pm - 4:00pm, The MILL @ UIdaho Library, University of Idaho - Moscow campus.

Dec

One AI to Rule Them All: How to Build a Large Multimodal Model (LMM) that Handles Text, Images, and Music - Data Hub Tech Talk

12:30pm - 1:30pm, Data Hub presentation / collaboration space, University of Idaho - Moscow campus.

View All Library Workshops