A multimodal language model, trained on a new annotated image-pair dataset and a recall-precision reinforcement reward, selects better advertising creatives and explains its choices, with measured offline and online gains.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative Reasoning
A multimodal language model, trained on a new annotated image-pair dataset and a recall-precision reinforcement reward, selects better advertising creatives and explains its choices, with measured offline and online gains.