Related papers: Probing Intersectional Biases in Vision-Language M…
We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of intersectional biases…
Text-to-image synthesis aims to generate a photo-realistic and semantic consistent image from a specific text description. The images synthesized by off-the-shelf models usually contain limited components compared with the corresponding…
Despite LLMs' explicit alignment against demographic stereotypes, they have been shown to exhibit biases under various social contexts. In this work, we find that LLMs exhibit concerning biases in how they associate solution veracity with…
While various approaches have recently been studied for bias identification, little is known about how implicit language that does not explicitly convey a viewpoint affects bias amplification in large language models. To examine the…
Vision-Language Models have demonstrated remarkable capabilities in understanding visual content, yet systematic biases in their spatial processing remain largely unexplored. This work identifies and characterizes a systematic spatial…
Large language models (LLMs) are increasingly proposed for detecting and responding to violent content online, yet their ability to reason about morally ambiguous, real-world scenarios remains underexamined. We present the first study to…
Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This success, however, has not translated as effectively to the…
As the real propagation environment becomes in creasingly complex and dynamic, millimeter wave beam prediction faces huge challenges. However, the powerful cross modal representation capability of vision-language model (VLM) provides a…
As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to…
In the battle against widespread online misinformation, a growing problem is text-image inconsistency, where images are misleadingly paired with texts with different intent or meaning. Existing classification-based methods for text-image…
Text-to-Image (TTI) generative models have shown great progress in the past few years in terms of their ability to generate complex and high-quality imagery. At the same time, these models have been shown to suffer from harmful biases,…
Text-to-Image (T2I) generation is enabling new applications that support creators, designers, and general end users of productivity software by generating illustrative content with high photorealism starting from a given descriptive text as…
Vision language models (VLMs) show promise in medical diagnosis, but their performance across demographic subgroups when using in-context learning (ICL) remains poorly understood. We examine how the demographic composition of demonstration…
Recent works have shown the effectiveness of Large Vision Language Models (VLMs or LVLMs) in image manipulation detection. However, text manipulation detection is largely missing in these studies. We bridge this knowledge gap by analyzing…
Vision-Language Models (VLMs) are trained on vast amounts of data captured by humans emulating our understanding of the world. However, known as visual illusions, human's perception of reality isn't always faithful to the physical world.…
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment between visual and textual representations is not fully…
Text-to-image diffusion models have made significant advancements in generating high-quality, diverse images from text prompts. However, the inherent limitations of textual signals often prevent these models from fully capturing specific…
In this paper, we investigate when and how visual representations learned by two different generative models diverge. Given two text-to-image models, our goal is to discover visual attributes that appear in images generated by one model but…
This work presents a novel strategy to measure bias in text-to-image models. Using paired prompts that specify gender and vaguely reference an object (e.g. "a man/woman holding an item") we can examine whether certain objects are associated…
Recent large-scale text-to-image diffusion models generate photorealistic images but often struggle to accurately depict interactions between humans and objects due to their limited ability to differentiate various interaction words. In…