Back to papers
September 2, 2026cs.IRcs.AIcs.CLcs.CV

ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering

Adrien Mialland, Marc Plantevit, Julien Gallois, Céline Robardet
Read on arXivDownload PDF
Categories

cs.IR, cs.AI, cs.CL, cs.CV

ViSAR: Training-Free Adaptive-$k$ Retrieval | One9Founders