Sivan Doveh

vision language model (4) compositional reasoning (3) zero-shot learning (2) object localization (2) weakly supervised learning (2) vision-language model (2) visual question answering (1) gradient-based optimization (1) benchmark evaluation (1) multimodal learning (1) semantic analysis (1) multi-modal learning (1) network pruning (1) neural architecture search (1) question answering (1) transfer learning (1) model pruning (1) image alignment (1) language model (1) visual grounding (1)