Using contrastive examples with vision-language models and a new CLIP-based scoring method called CSP produces more faithful and granular neuron labels than prior activation-only approaches.
In: The Thirteenth Interna- tional Conference on Learning Representations (2025),https://openreview.net/forum? id=tcsZt9ZNKD
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
Using contrastive examples with vision-language models and a new CLIP-based scoring method called CSP produces more faithful and granular neuron labels than prior activation-only approaches.