//
sign in
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
6/ Check out our paper and code šŸ‘‡ šŸ“„ Paper: arxiv.org/abs/2601.09322 šŸ’» Code: github.com/lciernik/att... #VisionTransformer #MachineLearning #AIResearch
4mo
With the rise of large-scale foundation models, efficiently adapting them to downstream tasks remains a central challenge. Linear probing, which freezes the backbone and trains a lightweight head, is ...
arxiv.org
Beyond the final layer: Attentive multilayer fusion for vision transformers
Laure Ciernik