arXiv subjects

Hieu Minh Nguyen

Publications and source records attributed to Hieu Minh Nguyen.

5 recordsLinked to original sources

arXiv2026

Dieu khien he da tac tu

Since the early 2000s, control of multiagent systems has attracted significant research interest, with applications ranging from natural collective behaviors and social dynamics to engineered systems such as autonomous vehicles, sensor networks, and smart grids. Although research on multi-agent systems has diversified into numerous specialized directions, textbooks -- including those in English -- that provide a systematic treatment of the fundamental principles of multi-agent system control remain scarce. The material presented in this book has been developed and used in teaching since 2021, initially as a concise Vietnamese-language reference for the courses Networked Control Systems and Control of Multi-Agent Systems at Hanoi University of Science and Technology. The book focuses on a selection of fundamental topics of broad and continuing interest in the field. The complexity of several topics is asymptotic to that encountered in research-level studies, however, the analysis is presented in a step-by-step manner to facilitate access to commonly used methods and tools. The material is divided into three main parts. Part I introduces multiagent systems and basic graph-theoretic concepts. Part II addresses the design and analysis of linear consensus algorithms. Part III covers selected applications and research directions, including formation control, network localization, distributed optimization, opinion dynamics, and matrix-weighted networks. Each chapter concludes with notes on notable researchers in this field, further reading, and exercises. This book cannot be completed without the encouragement, support and suggestions from families, colleagues and friends. The authors appreciate feedback from readers to further improve the content of the book.

cs.MA↗

arXiv2025

Towards Signboard-Oriented Visual Question Answering: ViSignVQA Dataset, Method and Benchmark

Understanding signboard text in natural scenes is essential for real-world applications of Visual Question Answering (VQA), yet remains underexplored, particularly in low-resource languages. We introduce ViSignVQA, the first large-scale Vietnamese dataset designed for signboard-oriented VQA, which comprises 10,762 images and 25,573 question-answer pairs. The dataset captures the diverse linguistic, cultural, and visual characteristics of Vietnamese signboards, including bilingual text, informal phrasing, and visual elements such as color and layout. To benchmark this task, we adapted state-of-the-art VQA models (e.g., BLIP-2, LaTr, PreSTU, and SaL) by integrating a Vietnamese OCR model (SwinTextSpotter) and a Vietnamese pretrained language model (ViT5). The experimental results highlight the significant role of the OCR-enhanced context, with F1-score improvements of up to 209% when the OCR text is appended to questions. Additionally, we propose a multi-agent VQA framework combining perception and reasoning agents with GPT-4, achieving 75.98% accuracy via majority voting. Our study presents the first large-scale multimodal dataset for Vietnamese signboard understanding. This underscores the importance of domain-specific resources in enhancing text-based VQA for low-resource languages. ViSignVQA serves as a benchmark capturing real-world scene text characteristics and supporting the development and evaluation of OCR-integrated VQA models in Vietnamese.

cs.CV↗

arXiv2025

Evaluating Precise Geolocation Inference Capabilities of Vision Language Models

The prevalence of Vision-Language Models (VLMs) raises important questions about privacy in an era where visual information is increasingly available. While foundation VLMs demonstrate broad knowledge and learned capabilities, we specifically investigate their ability to infer geographic location from previously unseen image data. This paper introduces a benchmark dataset collected from Google Street View that represents its global distribution of coverage. Foundation models are evaluated on single-image geolocation inference, with many achieving median distance errors of <300 km. We further evaluate VLM "agents" with access to supplemental tools, observing up to a 30.6% decrease in distance error. Our findings establish that modern foundation VLMs can act as powerful image geolocation tools, without being specifically trained for this task. When coupled with increasing accessibility of these models, our findings have greater implications for online privacy. We discuss these risks, as well as future work in this area.

cs.CV↗

arXiv2024

"Global is Good, Local is Bad?": Understanding Brand Bias in LLMs

Many recent studies have investigated social biases in LLMs but brand bias has received little attention. This research examines the biases exhibited by LLMs towards different brands, a significant concern given the widespread use of LLMs in affected use cases such as product recommendation and market analysis. Biased models may perpetuate societal inequalities, unfairly favoring established global brands while marginalizing local ones. Using a curated dataset across four brand categories, we probe the behavior of LLMs in this space. We find a consistent pattern of bias in this space -- both in terms of disproportionately associating global brands with positive attributes and disproportionately recommending luxury gifts for individuals in high-income countries. We also find LLMs are subject to country-of-origin effects which may boost local brand preference in LLM outputs in specific contexts.

cs.CL↗

arXiv2024

The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability

Interpretability techniques are valuable for helping humans understand and oversee AI systems. The SaTML 2024 CNN Interpretability Competition solicited novel methods for studying convolutional neural networks (CNNs) at the ImageNet scale. The objective of the competition was to help human crowd-workers identify trojans in CNNs. This report showcases the methods and results of four featured competition entries. It remains challenging to help humans reliably diagnose trojans via interpretability tools. However, the competition's entries have contributed new techniques and set a new record on the benchmark from Casper et al., 2023.

cs.LG↗