Skip to main content
Search

# Bézier Prompt Paths

1 related articles

Subscribe to updates
  1. arXiv

    When a frozen vision model switches tasks, how shared prompts travel costs more than where they land: Bézier paths cut shallow feature transport action from 4.50 to 3.20

    Frozen vision foundation models adapt to new tasks through a few prompt tokens shared across all images, and updating those prompts moves the image-feature distribution from one endpoint to another. Prior theory asked which endpoints prompts can reach; this work asks whether they can travel between them along the shortest path and quantifies the extra transport cost imposed by shared attention. In an exactly solvable attention model the reachable features form a cone, and with three distinct content normalizers same-sign endpoints that are not pure rescalings force a strictly positive extra cost. On ViT-B/16 with VTAB-1k, a quadratic Bézier prompt path trained on feature action lowers held-out transport action from 4.50 to 3.20 in the shallow configuration.

You’re all caught up