Pith. sign in

Interpreting and Editing Vision- Language Representations to Mitigate Hallucinations

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

Investigating Mechanisms for In-Context Vision Language Binding

cs.CV · 2025-05-28 · conditional · novelty 5.0

Vision-language models appear to bind an object's image tokens to its textual references through shared binding ID vectors in their activations, and these vectors can be swapped causally to change the model's answers.

citing papers explorer

Showing 1 of 1 citing paper.

  • Investigating Mechanisms for In-Context Vision Language Binding cs.CV · 2025-05-28 · conditional · none · ref 7

    Vision-language models appear to bind an object's image tokens to its textual references through shared binding ID vectors in their activations, and these vectors can be swapped causally to change the model's answers.