The Schedule
Workshop Day
January 3rd, 2023
January 3rd, 2023
Opening remarks by Larry Davis and introduction by Emily Webber 9:00 - 9:15am
9:15 - 10:15 am
Keynote talk 1 - Applications of large vision language models
Keynote talk 1 - Applications of large vision language models
R. Manmatha, Amazon
Break 10:00 - 10:10am
10:15 - 11:00am
Oral Presentations 1
Oral Presentations 1
Georg Hess, Yi Zhu, Kelly Lin
Coffee break and posters 11:00 - 11:30 am
11:30 - 12:30 pm
Keynote talk 2 - When faking your data actually helps - Learning vision from GANs, NeRFs, and Noise
Keynote talk 2 - When faking your data actually helps - Learning vision from GANs, NeRFs, and Noise
Phillip Isola, MIT
Lunch 12:30 - 1:30pm
1:30- 2:30pm
Keynote 3 - Scaling pretraining via self-supervised learning
Keynote 3 - Scaling pretraining via self-supervised learning
Abhinav Gupta, CMU
Break 2:30 - 2:40pm
2:40 - 3:30pm
Oral presentations 3
Oral presentations 3
Vlad Lialin, Justin Downes
Coffee break and posters - 3:30 - 4:00 pm
4:00 - 5:00 pm
Keynote talk 4 - How well does modern pretraining generalize to new domains and tasks?
Keynote talk 4 - How well does modern pretraining generalize to new domains and tasks?
Kate Saenko, Boston University