70 citations · 239 across the 45 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
MANCE: Manifold Aware Concept Erasure
Matan Avitan, Yoav Goldberg, Yanai Elazar
Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it. This is difficult because representations encode many co…
cs.LG2023★ 2 cited
The Bias Amplification Paradox in Text-to-Image Generation
Preethi Seshadri, Sameer Singh, Yanai Elazar
Bias amplification is a phenomenon in which models exacerbate biases or stereotypes present in the training data. In this paper, we study bias amplification in the text-to-image do…