pith. sign in

Concept-monitor: Understand- ing dnn training through individual neurons.arXiv preprint arXiv:2304.13346, 2023

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

Multimodal Concept Bottleneck Models

cs.CV · 2026-06-18 · unverdicted · novelty 5.0

MM-CBM adds dual concept bottleneck layers to CLIP to enable interpretable multimodal vision tasks, reporting up to 51.26% average accuracy gains over prior CBMs across four benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Multimodal Concept Bottleneck Models cs.CV · 2026-06-18 · unverdicted · none · ref 14

    MM-CBM adds dual concept bottleneck layers to CLIP to enable interpretable multimodal vision tasks, reporting up to 51.26% average accuracy gains over prior CBMs across four benchmarks.