Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Decoding the Functional Roles of Register and High-Norm Patch Tokens in Vision Transformers
Neel Varma, Andrew Rufail, Dipika Khullar +1
Self-supervised Vision Transformers (ViTs), such as DINOv2, learn rich visual representations, but the functions of their internal tokens remain poorly understood. Recent architect…
cs.AI2026
Synchronized Logit Steering: Real-world Steganography
Andrew Rufail, Aadi Dash, Onir Narahari +5
Steganography in large language models offers a way to embed hidden messages within natural-sounding text. Existing token and logit-level methods typically require the sender and r…