Evènement proposé par le Centre Inria de l’Université Grenoble Alpes et le laboratoire Gipsa-Lab :

We are thrilled to invite you to our upcoming Tech Café, which promises to be an engaging and insightful session on Multi-modal and Multi-task in Deep Learning.

To make the event even more enjoyable, we will be serving delicious pizzas! 🍕

Event Details:

Presentation Title: Multi-modal and Multi-task in Deep Learning

Abstract:
This talk will present the features of multi-task and multi-modal in Deep Learning research.

Pioneer models, such as CLIP and GLIP, will be explored to present the fundamentals of Vision/Language learning.

Their expected outcomes for Deep Learning research will be discussed: better world modeling, alignment, and explainability.

About the Presenter:
Mathias RÉUS is a final-year PhD student at GIPSA-LAB. He is working on extending the Person Re-Identification task.

His research aims to make the task more robust and practical by enriching the training process.

Agenda:

Presentation: 15 minutes
Q&A Session: 10 minutes
Networking and Discussion: Following the Q&A

We hope you can join us for this exciting event. Please register here: Clic to Register to confirm your attendance.