Know a great AI tool or AI news source? Submit it to AiByts
3 min read

Spread Too Thin: How Higher Resolution Dilutes a Vision Transformer's Attention, and a Training-Free Rescaling

A vision transformer read at a higher resolution than it was trained at spreads each attention row over many more patches, yet every row must still hand out exactly one unit of weight.

By Neil D. B. BrucearXiv - cs.CV (CV)

Read the full story

Originally published by arXiv - cs.CV (CV) on Nov 17, 2026.

Read on arXiv - cs.CV (CV)(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.