SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal TransportPublished byqbouniot.github.ioon •1 min readSimon Roschmann, Paul Krzakala, Sonia Mazelet, Quentin Bouniot, Zeynep AkataSotalignSemiSupervisedAlignmentUnimodalLearn moreShareLegalReport
