SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport.

Simon Roschmann Paul Krzakala Sonia Mazelet Quentin Bouniot Zeynep Akata SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport. 2026 February abs/2602.23353 CoRR https://doi.org/10.48550/arXiv.2602.23353 db/journals/corr/corr2602.html#abs-2602-23353 streams/journals/corr