arxiv
PublishedOctober 27, 2026 at 4:00 AM
LE-GDA: Layer Ensemble Gaussian Discriminant Analysis for Training-Free Few-Shot CLIP Adaptation
Publisher summary· verbatim
arXiv:2610.34901v1 Announce Type: cross Abstract: Training-free few-shot adaptation of vision-language models typically constructs a classifier from CLIP's final projected image representation, leaving intermediate representations unused. Combining them is not straightforward. Class scores from diff
Stay posted· Newsletter
Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.
Your email is used only to send The Bubble Brief. Privacy policy
Discussion
No replies yet. Be first.
The Bubble Brief
MON · WED · FRIRead AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.
Your email is used only to send The Bubble Brief. Privacy policy
Originally published on arxiv ↗