相关论文: Investigating Disability Representations in Text-t…

Learning-based Text-to-Image (TTI) models like Stable Diffusion have revolutionized the way visual content is generated in various domains. However, recent research has shown that nonnegligible social bias exists in current state-of-the-art…

As data-driven systems are increasingly deployed at scale, ethical concerns have arisen around unfair and discriminatory outcomes for historically marginalized groups that are underrepresented in training data. In response, work around AI…

Text-to-image (T2I) generative models can create vivid, realistic images from textual descriptions. As these models proliferate, they expose new concerns about their ability to represent diverse demographic groups, propagate stereotypes,…

Following the initial excitement, Text-to-Image (TTI) models are now being examined more critically. While much of the discourse has focused on biases and stereotypes embedded in large-scale training datasets, the sociotechnical dynamics of…

Text-to-Image artificial intelligence (AI) recently saw a major breakthrough with the release of Dall-E and its open-source counterpart, Stable Diffusion. These programs allow anyone to create original visual art pieces by simply providing…

While recent research suggests Large Language Models match human creative performance in divergent thinking tasks, visual creativity remains underexplored. This study compared image generation in human participants (Visual Artists and Non…

Vision-language models (VLMs) are increasingly deployed in socially sensitive applications, yet their behavior with respect to disability remains underexplored. We study disability aware descriptions for person centric images, where models…

Building equitable and inclusive NLP technologies demands consideration of whether and how social attitudes are represented in ML models. In particular, representations encoded in models often inadvertently perpetuate undesirable social…

Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes. Prior work addresses this in two ways. Closed-set approaches mitigate biases in…

We investigated the potential and limitations of generative artificial intelligence (AI) in reflecting the authors' cognitive processes through creative expression. The focus is on the AI-generated artwork's ability to understand human…

This research discusses the figurative tensions that arise when using portraits to represent individuals behind a dataset. In the broader effort to communicate European data related to depression, the Kiel Science Communication Network…

Existing text-to-image generative models reflect or even amplify societal biases ingrained in their training data. This is especially concerning for human image generation where models are biased against certain demographic groups. Existing…

Text-to-image generation models have grown in popularity due to their ability to produce high-quality images from a text prompt. One use for this technology is to enable the creation of more accessible art creation software. In this paper,…

The increasing deployment of artificial intelligence (AI) tools to inform decision making across diverse areas including healthcare, employment, social benefits, and government policy, presents a serious risk for disabled people, who have…

One of the latest applications of Artificial Intelligence (AI) is to generate images from natural language descriptions. These generators are now becoming available and achieve impressive results that have been used for example in the front…

Generative models are nowadays widely used to generate graphical content used for multiple purposes, e.g. web, art, advertisement. However, it has been shown that the images generated by these models could reinforce societal biases already…

Text-to-image models take a sentence (i.e., prompt) and generate images associated with this input prompt. These models have created award wining-art, videos, and even synthetic datasets. However, text-to-image (T2I) models can generate…

Explanatory images play a pivotal role in accessible and easy-to-read (E2R) texts. However, the images available in online databases are not tailored toward the respective texts, and the creation of customized images is expensive. In this…

According to the World Health Organization, more than one billion people worldwide have disabilities. The field of disability studies defines disability through a social lens; people are disabled to the extent that society creates…

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 domain using Stable Diffusion by comparing gender ratios in…