Introduces a fairness layer for deep learning models that guarantees output parity and an online primal-dual algorithm for aggregate fairness guarantees in streaming predictions with small batch sizes.
arXiv preprint arXiv:2308.00755 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
unclear 1representative citing papers
TES applies early global alignment then iterative CLIP-guided refinement to text embeddings in Stable Diffusion to mitigate bias while preserving quality.
T2I-BiasBench is a new 13-metric benchmark showing that text-to-image models amplify gender and beauty biases while collapsing cultural representations even in aligned systems like Gemini.
citing papers explorer
-
Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning
Introduces a fairness layer for deep learning models that guarantees output parity and an online primal-dual algorithm for aggregate fairness guarantees in streaming predictions with small batch sizes.
-
Training-Free Debiasing of Diffusion Models via CLIP-Guided Denoising Optimization
TES applies early global alignment then iterative CLIP-guided refinement to text embeddings in Stable Diffusion to mitigate bias while preserving quality.
-
T2I-BiasBench: A Multi-Metric Framework for Auditing Demographic and Cultural Bias in Text-to-Image Models
T2I-BiasBench is a new 13-metric benchmark showing that text-to-image models amplify gender and beauty biases while collapsing cultural representations even in aligned systems like Gemini.