Mid-scale MLLMs reach 62-88% object-level exact-match accuracy in zero-shot localized concept naming via closed-set prompting and an embedding-based Open-CoNa strategy across datasets.
CUBIC: Concept embeddings for unsupervised bias identification using VLMs,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Low-cost concept-based localized explanations: How far can we get with training-free approaches?
Mid-scale MLLMs reach 62-88% object-level exact-match accuracy in zero-shot localized concept naming via closed-set prompting and an embedding-based Open-CoNa strategy across datasets.