Cultural Competence

VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models

This research investigates both explicit and implicit social biases exhibited by Vision-Language Models (VLMs). The key distinction between these bias types lies in the level of awareness: explicit bias refers to conscious, intentional biases, while implicit bias operates subconsciously. To analyze explicit bias, we directly pose questions to VLMs related to gender and racial differences: (1) Mu...

Process-Supervised LLM Recommenders via Flow-guided Tuning

While large language models (LLMs) are increasingly adapted for recommendation systems via supervised fine-tuning (SFT), this approach amplifies popularity bias due to its likelihood maximization objective, compromising recommendation diversity and fairness. To address this, we present Flow-guided fine-tuning recommender (Flower), which replaces SFT with a Generative Flow Network (GFlowNet) fram...

AnomalyPainter: Vision-Language-Diffusion Synergy for Zero-Shot Realistic and Diverse Industrial Anomaly Synthesis

While existing anomaly synthesis methods have made remarkable progress, achieving both realism and diversity in synthesis remains a major obstacle. ...

Se-HiLo: Noise-Resilient Semantic Communication with High-and-Low Frequency Decomposition

Semantic communication has emerged as a transformative paradigm in next-generation communication systems, leveraging advanced artificial intelligenc...

CLICv2: Image Complexity Representation via Content Invariance Contrastive Learning

Unsupervised image complexity representation often suffers from bias in positive sample selection and sensitivity to image content. We propose CLICv...

Chameleon: On the Scene Diversity and Domain Variety of AI-Generated Videos Detection

Artificial intelligence generated content (AIGC), known as DeepFakes, has emerged as a growing concern because it is being utilized as a tool for sp...

Fine-Grained Bias Detection in LLM: Enhancing detection mechanisms for nuanced biases

Recent advancements in Artificial Intelligence, particularly in Large Language Models (LLMs), have transformed natural language processing by improv...

MatchMaker: Automated Asset Generation for Robotic Assembly

Robotic assembly remains a significant challenge due to complexities in visual perception, functional grasping, contact-rich manipulation, and perfo...

AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data

Recent advances in generative models have sparked research on improving model fairness with AI-generated data. However, existing methods often face ...

Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature Perturbation

One-class anomaly detection aims to detect objects that do not belong to a predefined normal class. In practice training data lack those anomalous s...

Development and Enhancement of Text-to-Image Diffusion Models

This research focuses on the development and enhancement of text-to-image denoising diffusion models, addressing key challenges such as limited samp...

Visual Cues of Gender and Race are Associated with Stereotyping in Vision-Language Models

Current research on bias in Vision Language Models (VLMs) has important limitations: it is focused exclusively on trait associations while ignoring ...

PathoPainter: Augmenting Histopathology Segmentation via Tumor-aware Inpainting

Tumor segmentation plays a critical role in histopathology, but it requires costly, fine-grained image-mask pairs annotated by pathologists. Thus, s...

Enhancing Collective Intelligence in Large Language Models Through Emotional Integration

This research investigates the integration of emotional diversity into Large Language Models (LLMs) to enhance collective intelligence. Inspired by ...

Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias

Score-based diffusion models have achieved incredible performance in generating realistic images, audio, and video data. While these models produce ...

Biased Heritage: How Datasets Shape Models in Facial Expression Recognition

In recent years, the rapid development of artificial intelligence (AI) systems has raised concerns about our ability to ensure their fairness, that ...

An Analytical Theory of Power Law Spectral Bias in the Learning Dynamics of Diffusion Models

We developed an analytical framework for understanding how the learned distribution evolves during diffusion model training. Leveraging the Gaussian...

Disentangled Knowledge Tracing for Alleviating Cognitive Bias

In the realm of Intelligent Tutoring System (ITS), the accurate assessment of students' knowledge states through Knowledge Tracing (KT) is crucial f...

Exploring Model Quantization in GenAI-based Image Inpainting and Detection of Arable Plants

Deep learning-based weed control systems often suffer from limited training data diversity and constrained on-board computation, impacting their rea...

On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process

The double descent phenomenon, which deviates from the traditional bias-variance trade-off theory, attracts considerable research attention; however...