Ron Litman

visual question answering (4) vision-language model (3) large language model (2) optical character recognition (2) multimodal learning (2) scene text recognition (2) document understanding (2) neural machine translation (1) information extraction (1) vision transformer (1) selective attention (1) convolutional neural network (1) sequence-to-sequence learning (1) benchmark dataset (1) visual representation (1) multimodal reasoning (1) attention mechanism (1) reference-free evaluation (1) vision-language task (1) vision language model (1)