PixMo Collection A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 9 items • Updated Mar 2 • 91
view article Article CinePile 2.0 - making stronger datasets with adversarial refinement +2 RuchitRawal, mfarre, somepago, lvwerra • Oct 23, 2024 • 19
FlexCap: Generating Rich, Localized, and Flexible Captions in Images Paper • 2403.12026 • Published Mar 18, 2024 • 2