ViRGo adaptively routes visual retrieval decisions in VLMs by estimating object scale from intrinsic localization heads combined with token confidence, matching patch retrieval on small objects, attention retrieval on large ones, and global processing when unnecessary.
arXiv preprint arXiv:2503.01222 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Look Before You Zoom: Adaptive Routing for the Resolution-Context Trade-off in Visual RAG
ViRGo adaptively routes visual retrieval decisions in VLMs by estimating object scale from intrinsic localization heads combined with token confidence, matching patch retrieval on small objects, attention retrieval on large ones, and global processing when unnecessary.