Filip Pavetic

model scaling (2) image captioning (2) vision transformer (2) few-shot learning (1) domain generalization (1) transfer learning (1) object detection (1) visual question answering (1) in-context learning (1) multimodal learning (1) scene representation (1) remote sensing (1) multiview learning (1) vision language model (1) vision-language model (1) novel view synthesis (1) object-centric learning (1) object-centric representation (1) slot attention (1) parameter efficiency (1)