Graphics and Human Computer Interfaces Commons^™

Exploring The Potential Of Large Language Models For Heterophilic Graphs, Yuxia Wu, Shujie Li, Yuan Fang, Chuan Shi

Research Collection School Of Computing and Information Systems

Large language models (LLMs) have presented significant opportunities to enhance various machine learning applications, including graph neural networks (GNNs). By leveraging the vast open-world knowledge within LLMs, we can more effectively interpret and utilize textual data to better characterize heterophilic graphs, where neighboring nodes often have different labels. However, existing approaches for heterophilic graphs overlook the rich textual data associated with nodes, which could unlock deeper insights into their heterophilic contexts. In this work, we explore the potential of LLMs for modeling heterophilic graphs and propose a novel two-stage framework: LLM-enhanced edge discriminator and LLM-guided edge reweighting. In the first …

Ai-Based Accessibility Widget (Aibaw) Shortcomings For Blind Web Users, Joshua A. Rovira

LSU Master's Theses

With legal, ethical, and financial motivations to make their websites more accessible, many businesses and sites have begun to employ the use of artificial intelligence (AI) based widgets to automatically make necessary modifications to their sites' pages and subdomains. In this work, we conduct a qualitative case study to determine the efficacy of these AI tools as they pertain specifically to blind users. We analyze pages from twelve websites using accessiBe's AI accessibility widget and provide a taxonomy of their violations against the Web Content Accessibility Guidelines (WCAG) 2.1 level AA compliance. We found each website to bear numerous violations …

Simplifying 3d Printing Using Natural Language Processing, Jared E. Rosenberger

Undergraduate Theses

3D printing is a crucial technology with many applications in different fields. To be able to use this technology to its full extent, expertise in computer aided design (CAD) technology and 3D modeling is required. Many people interested in 3D printing do not have this expertise and thus cannot build custom models, and are consequently forced to buy them instead. Natural language processing (NLP) is one tool that can vastly simplify 3D modeling for those lacking CAD experience. Using NLP, someone can simply dictate what they want to be able to print, and a computer can then build a 3D …

David B. Smith Chats With Monday 1.0, David B. Smith

Publications and Research

This document is an edited archival transcript of extended conversations between David B. Smith and an AI persona (“Monday 1.0,” GPT‑4o based) conducted in Spring 2025, prepared as a foundational primary source for subsequent scholarly and creative work. It records the emergence and testing of concepts related to human–AI collaboration (including “Balanced Blended Space”), as well as applied explorations in areas such as generative AI, quantum computing and music, virtual orchestras, multimodal performance, pedagogy, and the rhetoric of “pushback” in conversational systems. It also contains an extended section in which Monday and DB Smith co-curate a set of student research …

Towards Real-World Unsupervised Anomaly Detection For Images, Zhonghang Liu

Dissertations and Theses Collection (Open Access)

In the era of big data, data quality plays a critical role in computer vision, where the reliability and purity of training images are essential for optimal performance. When training models such as image classifiers and object detectors, the quality of the training data directly influences the success of the model. In other words, if the training dataset is contaminated, the model’s performance might accordingly decrease.

To address this challenge, unsupervised anomaly detection (UAD) has become an attractive research area. By automatically removing these anomalous data points, UAD can help improve the accuracy and robustness of machine learning models in …

Temporal Relational Graph Convolutional Networks For Financial Applications, Brindha Priyadarshini Jeyaraman

Dissertations and Theses Collection (Open Access)

The financial industry operates within a highly dynamic and interconnected ecosystem, presenting unique challenges for predictive modeling and decision-making. Accurately forecasting financial performance, assessing credit risk, detecting fraud, and ensuring compliance require methodologies that can capture complex temporal, relational, and contextual dependencies within financial data. This thesis investigates the use of Temporal Relational Graph Convolutional Networks (TRGCNs) combined with financial knowledge graphs (FKGs) to address these challenges and enable advanced analytics in the financial domain. We introduce FintechKG, a financial knowledge graph constructed through a threedimensional information extraction process, incorporating entities, temporal dimensions, and domain-specific financial relationships. A TRGCN-based framework …

Open-Set Graph Anomaly Detection Via Normal Structure Regularisation, Qizhou Wang, Guansong Pang, Mahsa Salehi, Xiaokun Xia, Christopher Leckie

Research Collection School Of Computing and Information Systems

This paper considers an important Graph Anomaly Detection (GAD) task, namely open-set GAD, which aims to train a detection model using a small number of normal and anomaly nodes (referred to as *seen anomalies*) to detect both seen anomalies and *unseen anomalies* (*i.e*., anomalies that cannot be illustrated the training anomalies). Those labelled training data provide crucial prior knowledge about abnormalities for GAD models, enabling substantially reduced detection errors. However, current supervised GAD methods tend to over-emphasise fitting the seen anomalies, leading to many errors of detecting the unseen anomalies as normal nodes. Further, existing open-set AD models were introduced …

One-For-All: Towards Universal Domain Translation With A Single Stylegan, Yong Du, Jiahui Zhan, Xinzhe Li, Junyu Dong, Sheng Chen, Ming-Hsuan Yang, Shengfeng He

Research Collection School Of Computing and Information Systems

In this paper, we propose a novel translation model, UniTranslator, for transforming representations between visually distinct domains under conditions of limited training data and significant visual differences. The main idea behind our approach is leveraging the domain-neutral capabilities of CLIP as a bridging mechanism, while utilizing a separate module to extract abstract, domain-agnostic semantics from the embeddings of both the source and target realms. Fusing these abstract semantics with target-specific semantics results in a transformed embedding within the CLIP space. To bridge the gap between the disparate worlds of CLIP and StyleGAN, we introduce a new non-linear mapper, the CLIP2P …

Sita: Structurally Imperceptible And Transferable Adversarial Attacks For Stylized Image Generation, Jingdan Kang, Haoxin Yang, Yan Cai, Huaidong Zhang, Xuemiao Xu, Yong Du, Shengfeng He

Research Collection School Of Computing and Information Systems

Image generation technology has brought significant advancements across various fields but has also raised concerns about data misuse and potential rights infringements, particularly with respect to creating visual artworks. Current methods aimed at safeguarding artworks often employ adversarial attacks. However, these methods face challenges such as poor transferability, high computational costs, and the introduction of noticeable noise, which compromises the aesthetic quality of the original artwork. To address these limitations, we propose a Structurally Imperceptible and Transferable Adversarial (SITA) attacks. SITA leverages a CLIP-based destylization loss, which decouples and disrupts the robust style representation of the image. This disruption hinders …

Samgpt: Text-Free Graph Foundation Model For Multi-Domain Pre-Training And Cross-Domain Adaptation, Xingtong Yu, Zechuan Gong, Chang Zhou, Yuan Fang, Hui Zhang

Research Collection School Of Computing and Information Systems

Graphs are able to model interconnected entities in many online services, supporting a wide range of applications on the Web. This raises an important question: How can we train a graph foundational model on multiple source domains and adapt to an unseen target domain? A major obstacle is that graphs from different domains often exhibit divergent characteristics. Some studies leverage large language models to align multiple domains based on textual descriptions associated with the graphs, limiting their applicability to text-attributed graphs. For text-free graphs, a few recent works attempt to align different feature distributions across domains, while generally neglecting structural …

Node-Time Conditional Prompt Learning In Dynamic Graphs, Xingtong Yu, Zhenghao Liu, Xinming Zhang, Yuan Fang

Research Collection School Of Computing and Information Systems

Dynamic graphs capture evolving interactions between entities, such as in social networks, online learning platforms, and crowdsourcing projects. For dynamic graph modeling, dynamic graph neural networks (DGNNs) have emerged as a mainstream technique. However, they are generally pre-trained on the link prediction task, leaving a significant gap from the objectives of downstream tasks such as node classification. To bridge the gap, prompt-based learning has gained traction on graphs, but most existing efforts focus on static graphs and neglect the evolution of dynamic graphs. In this paper, we propose DYGPROMPT, a novel pre-training and prompt learning framework for dynamic graph modeling. …

Minimum Multi-Service Fleet Size Problem: Shareability Graph And Network Flow Approach, Dingtong Yang, Yubin Liu, Hai Wang, Jinhua Zhao, Hamsa Balakrishnan

Research Collection School Of Computing and Information Systems

On-demand, vehicle-based services—such as ride-hailing, food, grocery, and parcel delivery—have become ubiquitous over the past decade. These services can be categorized into four types (Sun et al., 2023): passenger mobility, goods delivery, information acquisition (e.g., probe vehicle for traffic conditions), and mobile server (e.g., vehicle displaying advertisements). Passenger mobility and goods delivery are typically fulfilled by separate fleets, each dedicated to a single service. However, if various services can be pooled and handled simultaneously by a multi-functional fleet while maintaining service quality, the total number of required vehicles and overall vehicle mileage could be significantly reduced. This exciting potential motivates …

Ai Models By Boodlebox: Purpose-Built Intelligence, Kyle Horn

SACAD: Scholarly Activities

Generative AI has transformed the way we interact with technology, enabling dynamic and intelligent conversations through AI-driven bots. This project explores my experience with BoodleBox, a platform that hosts AI chatbots, offering users access to leading AI models such as ChatGPT, Gemini, DALL·E, and DeepSeek. Through the FHSU Generative AI Initiative, I was granted access to experiment with these models and create my own custom AI bot tailored to specific needs. This poster highlights the process of developing a custom bot, including defining instructions, enforcing rules, and sharing the bot for others to use. Additionally, it discusses the background of …

Application Of Graph Neural Networks With Phase Space Graphs, Parker H. Cole, Ryan Benton, Ralf Riedel, David Bourrie

Shelby Hall Graduate Research Forum Posters

Non-linear phase-space analysis models data represented as a graph transitioning between states in the time domain. By studying data transitions, we can predict the time a particular behavior occurs and classify the events (states) in a system. For example, we could classify neurological sensor data to determine if a person is asleep (state), or predict the direction in which a stock will move (transitions) based on micro trade patterns.

Previous research has demonstrated success in phase-space graphs in classifying malware, detecting network intrusions, and predicting seizures. However, the solutions either require calculating global graph features as inputs to a classifier, …

Topical Text Segmentation For Stream Of Consciousness Writing, Yuwei Lu, Ryan Benton

Shelby Hall Graduate Research Forum Posters

Stream of consciousness writing has a long history, including novelists James Joyce and Virginia Woolf. However, there has been little work done in automated and semi-automated analysis of such writing, which is the focus of this work. We plan to divide real streams of consciousness writing into distinct topical units and then capture different momentary meaningful topics from these units. By doing this, researchers and readers could gain a more nuanced understanding of the narrative structure and thematic elements. In addition, it would also support applications in fields like psychology and linguistics, where understanding thought processes and narrative structures is …

Imageinthat: Manipulating Images To Convey User Instructions To Robots, Karthik Mahadevan, Blaine Lewis, Jiannan Li, Bilge Mutlu, Anthony Tang, Tovi Grossman

Research Collection School Of Computing and Information Systems

Foundation models are rapidly improving the capability of robots in performing everyday tasks autonomously such as meal preparation, yet robots will still need to be instructed by humans due to model performance, the difficulty of capturing user preferences, and the need for user agency. Robots can be instructed using various methods---natural language conveys immediate instructions but can be abstract or ambiguous, whereas end-user programming supports longer-horizon tasks but interfaces face difficulties in capturing user intent. In this work, we propose using direct manipulation of images as an alternative paradigm to instruct robots, and introduce a specific instantiation called ImageInThat which …

Improving Multimodal Human Pose Estimation By Adversarial Modality Enhancement, Jiangnan Xia, Qilong Wu, Yanyin Guo, Yi Li, Jianghan Cheng, Junwei Li, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

Human pose estimation in computer vision predominantly focuses on the visible modality, with limited research on the infrared modality. No existing methods demonstrate robust performance across both modalities, missing their complementary strengths. This gap arises from the lack of a multimodal benchmark and the difficulty of developing robust multimodal capabilities. To address this, we introduce MMPD, a novel visible-infrared multimodal pose benchmark with high-quality annotations for both modalities. Leveraging MMPD, we expose the limitations of state-of-the-art methods due to modality variance. To overcome this challenge, we propose a novel method-agnostic scheme called AMMPE. By employing the Modality Adversarial Enhancement Stage …

Neurovig: Integrating Event Cameras For Resource-Efficient Video Grounding, Dulanga Weerakoon, Vigneshwaran Subbaraju, Joo Hwee Lim, Archan Misra

Research Collection School Of Computing and Information Systems

Spatio-Temporal Video Grounding (STVG) - the task of identifying the target object in the field-of-view that the language instruction refers to - is a fundamental vision-language task. Current STVG approaches typically utilize feeds from an RGB camera that is assumed to be always-on and process the video frames using complex neural network pipelines. As a result they often impose prohibitive system overheads (energy latency) on pervasive devices. To address this we propose NeuroViG with two key innovations: (a) leveraging on event streams from a low-power neuromorphic event camera sensor to perform selective triggering of the more energy-hungry RGB camera for …

Hand1000: Generating Realistic Hands From Text With Only 1,000 Images, Haozhuo Zhang, Bin Zhu, Yu Cao, Yanbin Hao

Research Collection School Of Computing and Information Systems

Text-to-image generation models have achieved remarkable advancements in recent years, aiming to produce realistic images from textual descriptions. However, these models often struggle with generating anatomically accurate representations of human hands. The resulting images frequently exhibit issues such as incorrect numbers of fingers, unnatural twisting or interlacing of fingers, or blurred and indistinct hands. These issues stem from the inherent complexity of hand structures and the difficulty in aligning textual descriptions with precise visual depictions of hands. To address these challenges, we propose a novel approach named Hand1000 that enables the generation of realistic hand images with target gesture using …

Lightprof: A Lightweight Reasoning Framework For Large Language Model On Knowledge Graph, Tu Ao, Yanhua Yu, Yuling Wang, Yang Deng, Zirui Guo, Liang Pang, Pinghui Wang, Tat-Seng Chua, Xiao Zhang, Zhen Cai

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have impressive capabilities in text understanding and zero-shot reasoning. However, delays in knowledge updates may cause them to reason incorrectly or produce harmful results. Knowledge Graphs (KGs) provide rich and reliable contextual information for the reasoning process of LLMs by structurally organizing and connecting a wide range of entities and relations. Existing KG-based LLM reasoning methods only inject KGs’ knowledge into prompts in a textual form, ignoring its structural information. Moreover, they mostly rely on close-source models or open-source models with large parameters, which poses challenges to high resource consumption. To address this, we propose a …