Sebastian Goodman

large language model (2) vision language model (2) image captioning (2) model scaling (2) visual question answering (2) multimodal learning (2) in-context learning (1) text summarization (1) distributed computing (1) vision-language model (1) data pipeline (1) exposure bia (1) pac-bayesian theory (1) optical character recognition (1) teacher forcing (1) text recognition (1) image feature extraction (1) neural network (1) multilingual vision language model (1) scene text understanding (1)