80%Must read
?Must readVote to see the score
Learning Dynamic Evidence Routes for Vision Transformer Probing
SSMProbe replaces invariant pooling with a Sinkhorn-learned evidence route and diagonal S4 decoder to audit frozen ViT token routing, finding MAE uses dispersed routes while BEiT, ViT, and DINOv2 use spatially organized ones.
Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026
– ReadersNo votes yet
12/20 AI panelreviewers recommend it
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
AI panel: 12 of 20 reviewers recommend it
lenient 2/5
medium 8/10
strict 2/5