One Model for All the Tasks - BLIP - Author Interview

One Model for All the Tasks - BLIP - Author Interview

Yannic Kilcher via YouTube Direct link

- Intro

1 of 15

1 of 15

- Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

One Model for All the Tasks - BLIP - Author Interview

Automatically move to the next video in the Classroom when playback concludes

  1. 1 - Intro
  2. 2 - Sponsor: Assembly AI
  3. 3 - Start of Interview
  4. 4 - What's the pitch?
  5. 5 - How did data bootstrapping come into the project?
  6. 6 - How big of a problem is data quality?
  7. 7 - Are the captioning & filtering models biased towards COCO data?
  8. 8 - Could the data bootstrapping be done multiple times?
  9. 9 - What was the evolution of the BLIP architecture?
  10. 10 - Are there additional benefits to adding language modelling?
  11. 11 - Can we imagine a modular future for pre-training?
  12. 12 - Diving into the experimental results
  13. 13 - What did and did not work out during the research?
  14. 14 - How is research life at Salesforce?
  15. 15 - Where do we go from here?

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.