Probabilistic Language-Image Pre-TrainingInternational Conference on Learning Representations (ICLR), 2024 |
Compositional Entailment Learning for Hyperbolic Vision-Language ModelsInternational Conference on Learning Representations (ICLR), 2024 Avik Pal Max van Spengler Guido Maria DÁmely di Melendugno Alessandro Flaborea Fabio Galasso Pascal Mettes |
3VL: Using Trees to Improve Vision-Language Models' InterpretabilityIEEE Transactions on Image Processing (IEEE TIP), 2023 |