Elad Ben Avraham

document understanding (2) video understanding (2) vision-language model (2) large language model (2) visual question answering (2) action recognition (2) vision transformer (2) reference-free evaluation (1) multimodal reasoning (1) scene structure (1) visual understanding (1) multi-page document (1) optical character recognition (1) token reduction (1) vision language (1) visual feature alignment (1) document visual question answering (1) global reasoning (1) question-aware encoding (1) query-based learning (1)