08:30am - Welcome (5min)
08:35am - Keynote Talk by Ludwig Schmidt (Stanford, Anthropic) (25min + 5min QA)
Title: LAION-5B & DataComp: In search of the next generation of multimodal datasets
09:05am - Keynote Talk by Arsha Nagrani (Google AI) (25min + 5min QA)
Title: How good are foundation models at video?
09:35am - Poster session (Poster boards #31 - #66 in ExHall D at 9:40am – 11:00am) + Coffee break
10:30am - Keynote Talk by Andrew Owens (University of Michigan) (25min + 5min QA)
Title: Multimodal Learning from the Bottom Up
11:00am - Keynote Talk by Ani Kembhavi (University of Washington, Wayne AI) (25min + 5min QA)
Title: Synthetic By Design: The Future of Data is Modelled
11:30am - Panel Discussion: What is Next in Multimodal Foundation Models? (40min)
Moderator: Roei Herzig (UC Berkeley)
Panelists: Ludwig Schmidt, Andrew Owens, Arsha Nagrani, Ani Kembhavi
12:10pm - Concluding Remarks (5min)
12:15pm - Adjourn