arXiv - CSCL: "MMHQA-ICL: Multimodal In-context Learning for Hyb…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images. (arXiv:2309.04790v1 [cs.CL])

http://arxiv.org/abs/2309.04790 #arXiv #NLProc

Sep 12, 2023, 03:17 · · arxiv-cscl · · ·

Sign in to participate in the conversation