arXiv - CSCL: "PEVL: Position-enhanced Pre-training and Prompt T…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models. (arXiv:2205.11169v2 [cs.CV] UPDATED)

http://arxiv.org/abs/2205.11169 #arXiv #NLProc

Nov 23, 2022, 03:20 · · arxiv-cscl · · ·

Sign in to participate in the conversation