Ryota Tanaka

visual question answering (3) document image (2) document understanding (2) dense retrieval (1) instruction tuning (1) vision-language model (1) multimodal large language model (1) retrieval-augmented generation (1) self-supervised pre-training (1) multi-image reasoning (1) visual document understanding (1) numerical reasoning (1) evidence selection (1) document visual question answering (1) visually-rich document (1) visual layout modeling (1) document image understanding (1) sequence to sequence model (1) visual machine reading comprehension (1) pre trained language model (1)