Cultural Competence

Entropy Rectifying Guidance for Diffusion and Flow Models

Guidance techniques are commonly used in diffusion and flow models to improve image quality and consistency for conditional generative tasks such as class-conditional and text-to-image generation. In particular, classifier-free guidance (CFG) -- the most widely adopted guidance technique -- contrasts conditional and unconditional predictions to improve the generated images. This results, however...

Uncovering an Attractiveness Bias in Multimodal Large Language Models: A Case Study with LLaVA

Physical attractiveness matters. It has been shown to influence human perception and decision-making, often leading to biased judgments that favor those deemed attractive in what is referred to as "the attractiveness halo effect". While extensively studied in human judgments in a broad set of domains, including hiring, judicial sentencing or credit granting, the role that attractiveness plays in...

Real-World Depth Recovery via Structure Uncertainty Modeling and Inaccurate GT Depth Fitting

The low-quality structure in raw depth maps is prevalent in real-world RGB-D datasets, which makes real-world depth recovery a critical task in rece...

Bridging the Semantic Gaps: Improving Medical VQA Consistency with LLM-Augmented Question Sets

Medical Visual Question Answering (MVQA) systems can interpret medical images in response to natural language queries. However, linguistic variabili...

Using LLMs as prompt modifier to avoid biases in AI image generators

This study examines how Large Language Models (LLMs) can reduce biases in text-to-image generation systems by modifying user prompts. We define bias...

Name of Thrones: Evaluating How LLMs Rank Student Names, Race, and Gender in Status Hierarchies

Across cultures, names tell a lot about their bearers as they carry deep personal and cultural significance. Names also serve as powerful signals of...

Artificial Intelligence in Cancer Care: Addressing Challenges and Health Equity.

Overdiagnosis in cancer care remains a significant concern, often resulting in unnecessary physical, emotional, and financial burdens on patients. Art...

Graph-Based Prediction Models for Data Debiasing

Bias in data collection, arising from both under-reporting and over-reporting, poses significant challenges in critical applications such as healthc...

Linguistic Comparison of AI- and Human-Written Responses to Online Mental Health Queries

The ubiquity and widespread use of digital and online technologies have transformed mental health support, with online mental health communities (OM...

Mixture of Group Experts for Learning Invariant Representations

Sparsely activated Mixture-of-Experts (MoE) models effectively increase the number of parameters while maintaining consistent computational costs pe...

Mixed Signals: Decoding VLMs' Reasoning and Underlying Bias in Vision-Language Conflict

Vision-language models (VLMs) have demonstrated impressive performance by effectively integrating visual and textual information to solve complex ta...

ELSA: A Style Aligned Dataset for Emotionally Intelligent Language Generation

Advancements in emotion aware language processing increasingly shape vital NLP applications ranging from conversational AI and affective computing t...

DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows

Many real-world applications of flow-based generative models desire a diverse set of samples that cover multiple modes of the target distribution. H...

Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge

Large Language Models (LLMs) have revolutionized artificial intelligence, driving advancements in machine translation, summarization, and conversati...

ID-Booth: Identity-consistent Face Generation with Diffusion Models

Recent advances in generative modeling have enabled the generation of high-quality synthetic data that is applicable in a variety of domains, includ...

Language-Dependent Political Bias in AI: A Study of ChatGPT and Gemini

As leading examples of large language models, ChatGPT and Gemini claim to provide accurate and unbiased information, emphasizing their commitment to...

On the Dynamics of Mating Preferences in Genetic Programming

Several mating restriction techniques have been implemented in Evolutionary Algorithms to promote diversity. From similarity-based selection to nich...

Challenges of Artificial Intelligence in Medicine.

Artificial Intelligence (AI) holds great promise for healthcare, promising improved patient outcomes and streamlining processes. Nevertheless, this tr...

Deconstructing Bias: A Multifaceted Framework for Diagnosing Cultural and Compositional Inequities in Text-to-Image Generative Models

The transformative potential of text-to-image (T2I) models hinges on their ability to synthesize culturally diverse, photorealistic images from text...

Cognitive Debiasing Large Language Models for Decision-Making

Large language models (LLMs) have shown potential in supporting decision-making applications, particularly as personal assistants in the financial, ...