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