pith. sign in

A higher score indicates that the concept t is a better match for the neuronn

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

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

LINE: LLM-based Iterative Neuron Explanations for Vision Models

cs.CV · 2026-04-09 · unverdicted · novelty 8.0 · 2 refs

LINE iteratively refines open-vocabulary neuron concepts in vision models via LLM proposals and text-to-image testing, achieving up to 0.11 AUC gains on ImageNet while uncovering 27% new concepts missed by fixed vocabularies.

citing papers explorer

Showing 1 of 1 citing paper.

  • LINE: LLM-based Iterative Neuron Explanations for Vision Models cs.CV · 2026-04-09 · unverdicted · none · ref 4 · 2 links

    LINE iteratively refines open-vocabulary neuron concepts in vision models via LLM proposals and text-to-image testing, achieving up to 0.11 AUC gains on ImageNet while uncovering 27% new concepts missed by fixed vocabularies.