IR-guided diffusion injects intermediate text representations into early denoising steps to improve alignment for one-and-only objects, reporting up to 19.1pp VQAScore gains on OAO-AttackBench and other benchmarks.
Debiasing vision-language models via biased prompts
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
verdicts
UNVERDICTED 7representative citing papers
DAT rescales CLIP image-text similarities based on local embedding density to reduce the impact of spurious correlations in zero-shot classification.
StayFair addresses guidance bias in diffusion models by extending demographic parity, allowing fairness to hold across guidance scales via modified classifier or null-embedding steps.
Embedding Arithmetic performs vector operations in the embedding space of T2I models to mitigate bias at inference time, outperforming baselines on diversity while preserving coherence via a new Concept Coherence Score.
POVID generates AI-created preference data to fine-tune vision-language models with DPO, reducing hallucinations and improving benchmark scores.
Vision-language models for wellbeing assessment exhibit dataset-dependent performance and demographic biases, with explainability interventions providing inconsistent fairness gains at potential accuracy costs.
A systematic review of T2I bias literature that distinguishes target and threshold fairness and proposes a target-based operationalization framework.
citing papers explorer
-
Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment
IR-guided diffusion injects intermediate text representations into early denoising steps to improve alignment for one-and-only objects, reporting up to 19.1pp VQAScore gains on OAO-AttackBench and other benchmarks.
-
Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
DAT rescales CLIP image-text similarities based on local embedding density to reduce the impact of spurious correlations in zero-shot classification.
-
Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales
StayFair addresses guidance bias in diffusion models by extending demographic parity, allowing fairness to hold across guidance scales via modified classifier or null-embedding steps.
-
Embedding Arithmetic: A Lightweight, Tuning-Free Framework for Post-hoc Bias Mitigation in Text-to-Image Models
Embedding Arithmetic performs vector operations in the embedding space of T2I models to mitigate bias at inference time, outperforming baselines on diversity while preserving coherence via a new Concept Coherence Score.
-
Aligning Modalities in Vision Large Language Models via Preference Fine-tuning
POVID generates AI-created preference data to fine-tune vision-language models with DPO, reducing hallucinations and improving benchmark scores.
-
FAIR_XAI: Improving Multimodal Foundation Model Fairness via Explainability for Wellbeing Assessment
Vision-language models for wellbeing assessment exhibit dataset-dependent performance and demographic biases, with explainability interventions providing inconsistent fairness gains at potential accuracy costs.
-
Operationalizing Fairness in Text-to-Image Models: A Survey of Bias, Fairness Audits and Mitigation Strategies
A systematic review of T2I bias literature that distinguishes target and threshold fairness and proposes a target-based operationalization framework.