Physical Sciences and Mathematics Commons^™

Graph Foundation Models: Concepts, Opportunities And Challenges, Jiawei Liu, Cheng Yang, Zhiyuan Lu, Junze Chen, Yibo Li, Mengmei Zhang, Ting Bai, Fang Yuan, Lichao Sun, Philip S. Yu, Chuan Shi

Research Collection School Of Computing and Information Systems

Foundation models have emerged as critical components in a variety of artificial intelligence applications, and showcase significant success in natural language processing and several other domains. Meanwhile, the field of graph machine learning is witnessing a paradigm transition from shallow methods to more sophisticated deep learning approaches. The capabilities of foundation models in generalization and adaptation motivate graph machine learning researchers to discuss the potential of developing a new graph learning paradigm. This paradigm envisions models that are pre-trained on extensive graph data and can be adapted for various graph tasks. Despite this burgeoning interest, there is a noticeable lack …

Leveraging Constraint Violation Signals For Action Constrained Reinforcement Learning, Janaka Chathuranga Brahmanage, Jiajing Ling, Akshat Kumar

Research Collection School Of Computing and Information Systems

In many RL applications, ensuring an agent’s actions adhere to constraints is crucial for safety. Most previous methods in Action-Constrained Reinforcement Learning (ACRL) employ a projection layer after the policy network to correct the action. However projection-based methods suffer from issues like the zero gradient problem and higher runtime due to the usage of optimization solvers. Recently methods were proposed to train generative models to learn a differentiable mapping between latent variables and feasible actions to address this issue. However, generative models require training using samples from the constrained action space, which itself is challenging. To address such limitations, first, …

Occlusion-Insensitive Talking Head Video Generation Via Facelet Compensation, Yuhui Deng, Yuqin Lu, Yangyang Xu, Yongwei Nie, Shengfeng He

Research Collection School Of Computing and Information Systems

Talking head video generation involves animating a still face image using facial motion cues derived from a driving video to replicate target poses and expressions. Traditional methods often rely on the assumption that the relative positions of facial keypoints remain unchanged. However, this assumption fails when keypoints are occluded or when the head is in a profile pose, leading to inconsistencies in identity and blurring in certain facial regions. In this paper, we introduce Occlusion-Insensitive Talking Head Video Generation, a novel approach that eliminates the reliance on spatial correlation of keypoints and instead leverages semantic correlation. Our method transforms facial …

Marginal Benefit Driven Rl Teacher For Unsupervised Environment Design, Dexun Li, Wenjun Li, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Training generally capable agents in complex environments is a challenging task that involves identifying the “right” environments at the training stage. Recent research has highlighted the potential of the Unsupervised Environment Design framework, which generates environment instances/levels adaptively at the frontier of the agent’s capabilities using regret measures. While regret approaches have shown promise in generating feasible environments, they can produce difficult environments that are challenging for an RL agent to learn from. This is because regret represents the best-case (upper bound) learning potential and not the actual learning potential of an environment. To address this, we propose an alternative …

Adapting Knowledge Prompt Tuning For Enhanced Automated Program Repair, Xuemeng Cai, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Automated Program Repair (APR) aims to enhance software reliability by automatically generating bug-fixing patches. Recent work has improved the state-of-the-art of APR by fine-tuning pre-trained large language models (LLMs), such as CodeT5, for APR. However, the effectiveness of fine-tuning be-comes weakened in data scarcity scenarios, and data scarcity can be a common issue in practice, limiting fine-tuning performance. To alleviate this limitation, this paper adapts prompt tuning for enhanced APR and conducts a comprehensive study to evaluate its effectiveness in data scarcity scenarios, using three LLMs of different sizes and six diverse datasets across four programming languages. Prompt tuning rewrites …

Adaptive Deviation Learning For Visual Anomaly Detection With Data Contamination, Aanindya Sundar Das, Guansong Pang, Monowar Bhuyan

Research Collection School Of Computing and Information Systems

Visual anomaly detection targets to detect images that notably differ from normal pattern, and it has found extensive application in identifying defective parts within the manufacturing industry. These anomaly detection paradigms predominantly focus on training detection models using only clean, unlabeled normal samples, assuming an absence of contamination; a condition often unmet in real-world scenarios. The performance of these methods significantly depends on the quality of the data and usually decreases when exposed to noise. We introduce a systematic adaptive method that employs deviation learning to compute anomaly scores end-to-end while addressing data contamination by assigning relative importance to the …

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 …

Generalization Analysis For Deep Contrastive Representation Learning, Minh Hieu Nong, Antoine Ledent, Yunwen Lei, Cheng Yeaw Ku

Research Collection School Of Computing and Information Systems

In this paper, we present generalization bounds for the unsupervised risk in the Deep Contrastive Representation Learning framework, which employs deep neural networks as representation functions. We approach this problem from two angles. On the one hand, we derive a parameter-counting bound that scales with the overall size of the neural networks. On the other hand, we provide a norm-based bound that scales with the norms of neural networks’ weight matrices. Ignoring logarithmic factors, the bounds are independent of k, the size of the tuples provided for contrastive learning. To the best of our knowledge, this property is only shared …

Revisiting Sentiment Analysis For Software Engineering In The Era Of Large Language Models, Ting Zhang, Ivana Clairine Irsan, Thung Ferdian, David Lo

Research Collection School Of Computing and Information Systems

Software development involves collaborative interactions where stakeholders express opinions across various platforms. Recognizing the sentiments conveyed in these interactions is crucial for the effective development and ongoing maintenance of software systems. For software products, analyzing the sentiment of user feedback, e.g., reviews, comments, and forum posts can provide valuable insights into user satisfaction and areas for improvement. This can guide the development of future updates and features. However, accurately identifying sentiments in software engineering datasets remains challenging.This study investigates bigger large language models (bLLMs) in addressing the labeled data shortage that hampers fine-tuned smaller large language models (sLLMs) in software …

Understanding Individual Agent Importance In Multi-Agent System Via Counterfactual Reasoning, Jianming Chen, Yawen Wang, Junjie Wang, Xiaofei Xie, Jun Hu, Qing Wang, Fanjiang Xu

Research Collection School Of Computing and Information Systems

Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has provided explanations for the actions or states of agents, yet falls short in understanding the black-boxed agent's importance within a MAS and the overall team strategy. To bridge this gap, we propose EMAI, a novel agent-level explanation approach that evaluates the individual agent's importance. Inspired by counterfactual reasoning, a larger change in reward caused by the randomized action of agent indicates its higher importance. We model it as a MARL problem to capture interactions across agents. Utilizing counterfactual reasoning, EMAI learns the …

Backdoor Token Unlearning: Exposing And Defending Backdoors In Pretrained Language Models, Peihai Jiang, Xixiang Lyu, Yige Li, Jing Ma

Research Collection School Of Computing and Information Systems

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of malicious samples can successfully embed backdoor triggers into the model. While most existing defense methods focus on post-training backdoor defense, efficiently defending against backdoor attacks during training phase remains largely unexplored. To address this gap, we propose a novel defense method called Backdoor Token Unlearning (BTU), which proactively detects and neutralizes trigger tokens during the training stage. Our work is based on two key findings: 1) …

Sticky Information Technology Investment: Theory And Empirical Evidence, Peng Liang, Hasan Cavusoglu, Nan Hu

Research Collection School Of Computing and Information Systems

This article provides a new way of thinking about managerial discretion in information technology (IT) investment decisions. We delve into the existence, antecedents, and consequences of sticky IT investment behavior, an understudied managerial deliberate resource commitment decision in response to changes in sales. Guided by downsizing theory, we initially theorize and find that IT investments exhibit stickiness: IT investments move downward less for sales decreases than they move upward for equivalent increases. Then drawing upon agency theory, adjustment costs theory, and managerial expectations theory—which influence managers’ motivation for downsizing—we predict and demonstrate that managers’ empire-building incentives, their avoidance of adjustment …

Understanding The Oss Communities Of Deep Learning Frameworks: A Comparative Case Study Of Pytorch And Tensorflow, Yunqi Chen, Zhiyuan Wan, Yifei Zhuang, Ning Liu, David Lo, Xiaohu Yang

Research Collection School Of Computing and Information Systems

Over the past two decades, deep learning has received tremendous success in developing software systems across various domains. Deep learning frameworks have been proposed to facilitate the development of such software systems, among which, PyTorch and TensorFlow stand out as notable examples. Considerable attention focuses on exploring software engineering practices and addressing diverse technical aspects in developing and deploying deep learning frameworks and software systems. Despite these efforts, little is known about the open source software communities involved in the development of deep learning frameworks. In this article, we perform a comparative investigation into the open source software communities of …

Deepvmunprotect: Neural Network-Based Recovery Of Vm‑Protected Android Apps For Semantics‑Aware Malware Detection, Xin Zhao, Mu Zhang, Xiaopeng Ke, Yu Pan, Yue Duan, Sheng Zhong, Fengyuan Xu

Research Collection School Of Computing and Information Systems

The emerging virtual machine-based Android packers render existing unpacking techniques ineffective. The state-of-the-art unpacker falls short because it relies on unreliable heuristics and manually crafted semantic models. Hence, it cannot precisely recover app semantics necessary for malware detection. In this paper, we propose DeepVMUnProtect, a deep learning-based approach to automatically and accurately capture the semantics of VM-packed code, so as to facilitate semantic-based Android malware classification. Experiments have shown that DeepVMUnProtect outperforms the state-of-the-art tool on recovering opcode semantics in Qihoo(58.3%), Baidu(47.5%) and NMMP (58.8%) respectively, and can enable semantics-aware malware detection which prior work fails to do.

Environmental Justice And Ecology In Social Work Education: Emerging Trends Among Faculty., Keri Otte

Doctor of Social Work Capstone Projects

March 31, 2025

This paper presents a study of how social work educators in the U.S. are integrating environmental justice and ecological content into social work coursework and /or curriculum. Current literature in this area suggests that educators should be incorporating deep ecology philosophy, using experiential learning techniques, and moving away from anthropocentrism towards ecocentrism. Ten semi-structured interviews were conducted to gather data on pedagogical approaches, educator knowledge and previous training, and barriers to content integration. The interviews took place virtually with social work educators from five geographical areas in the United States. The findings illustrate the importance of transformative …

Exploring Intelligent Manufacturing: How Artificial Intelligence Affects Productivity And Labor Demand At The Enterprise Level, Jie Gu

Dissertations and Theses Collection (Open Access)

Manufacturing is a cornerstone of national economic health and social stability, yet it faces challenges such as declining profits, rising labor costs, and an aging workforce. In China, the manufacturing sector is undergoing a critical transformation, driven by technological advancements like artificial intelligence (AI) and the push for intelligent manufacturing. This study explores how AI revitalizes the manufacturing sector by enhancing enterprise productivity and reshaping labor demand, with a focus on quality inspection processes. Using a leading bearing factory as a case study, the research employs econometric models, A/B testing, and interviews to quantify AI’s impact on production efficiency, costs, …

Technical Memorandum - Re: 2022 Butte Priority Soils Operable Unit (Bpsou) Groundwater Compliance Evaluation, Paddy Stoy

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Draft Final - Silver Bow Creek Conservation Area (Sbcca) Butte Reduction Works (Brw) Air Monitoring For Interim Demolition Activities – Phase I Data Summary Report (Dsr), Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Draft Final 2022 Unreclaimed Sites Sampling: Ur-20 Site Evaluation Summary Report, Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Draft Final 2022 Unreclaimed Sites Sampling: Ur-22 Site Evaluation Summary Report, Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Revised Final Multi-Pathway Residential Metals Abatement Program Plan, Atlantic Richfield Company, Butte Silver Bow

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Draft Final Butte Priority Soils Operable Unit (Bpsou) Unreclaimed (Ur) Sites New And Mahoney (Ur-23) Construction Completion Report (Ccr), Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Modifiable And Non-Modifiable Risk Factors For Dementia Among Non-Hispanic White And Black Populations Aged 50-64 In The United States, 2006-2016, Jingkai Wei, Matthew C. Lohman Ph.D., Monique J. Brown, James W. Hardin, Chih-Hsiang Yang, Anwar T. Nerchant, Daniela B. Friedman

Faculty Publications

Background and Objectives

Research Design and Methods

Adverse Childhood Experiences, Resilience, And Syringe Services Program Attendance Among Persons Who Inject Drugs In Northeast Georgia, Usa: A Mediation Analysis, Mohammad Rifat Haider, Samantha Clinton, Monique J. Brown, Nathan B. Hansen

Faculty Publications

Background: Syringe services programs (SSP) are evidence-based venues offering harm reduction services to persons who inject drugs (PWID), such as sterile syringes, STI/HIV testing, and linkage to care to decrease drug use-related morbidities and mortalities. Adverse childhood experiences (ACEs) have been linked with reduced resilience, while increased resilience can help PWID attend SSPs. This study examined the potential mediating role of resilience between ACEs and SSP attendance among PWID.

Methods: Data were collected from adult HIV-negative PWID in northeast Georgia, between February-December 2023 (N = 173). Data were collected on SSP attendance (Yes vs. No), resilience, and ACEs. Covariates included …

Geographic Disparities In Unpaid Caregiving, Emma Kathryn Boswell, Monique J. Brown Ph.D., Mph, Lorie Donelle Phd, Rn, Fcan, Nicholas Yell, Taryn Farrell, Peiyin Hung Ph.D., Elizabeth Crouch Ph.D.

Faculty Publications

Purpose: An updated, nationally representative examination of rural–urban differences in the experiences, health, and well-being of caregivers is needed; previous research on this topic uses older data or has limited generalizability. This study examines rural–urban differences in the characteristics, experiences, and health of caregivers. Methods: The 2021–2022 Behavioral Risk Factor Surveillance System (n = 44,274 unpaid caregivers) was used, with rurality defined according to the 2013 National Center for Health Statistics (NCHS) Urban-Rural Classification Scheme. Chi-square tests compared rural–urban differences in these caregivers’ characteristics, including demographic factors, caregiving intensity (e.g., weekly hours spent caregiving, reason for caregiving, past-month ADL/IADL assistance), …

Characterization Of Btex Species At Texas Commission On Environmental Quality (Tceq) Continuous Ambient Monitoring Station (Cams) Sites In Houston, Texas, Usa During 2018, Amit U. Raysoni, Sai Deepak Pinakana, August Luna, Esmeralda Mendez, Gabriel Ibarra-Mejia

School of Earth, Environmental, & Marine Sciences Faculty Publications

Volatile Organic Compounds (VOCs) in the atmosphere negatively impact human and environmental health. Various sources of VOCs include gasoline evaporation, solvent usage, traffic, etc. A dataset 1-year (2018) consisting of BTEX (benzene, toluene, ethylbenzene, and m, p, and o-xylenes) concentrations in Houston, Texas, was analyzed to understand the spatial trends and sources of BTEX in the region. This study assesses 24-hour data concentrations from the Continuous Ambient Monitoring Station (CAMS) operated by the TCEQ Texas Commission on Environmental Quality (TCEQ) in Houston. Spatial variations of the BTEX species across the various TCEQ CAMS sites were determined using multiple statistical analyses, …

Book Vi Of The Mathematical Collection Of Pappus Of Alexandria, Translated By John B. Little, John B. Little, Pappus Of Alexandria

Holy Cross Bookshelf

Book VI of the Mathematical Collection is a collection of comments or notes about various points treated in parts of a collection of other texts sometimes known as the “Little Astronomy.” Pappus uses these works as sources and frequently quotes from them in this book. In the teaching of mathematical astronomy in late antiquity, and this would include the time of Pappus, the “Little Astronomy” is often understood to have been a follow-up to Euclid’s Elements and a preliminary to the study of the Almagest of Claudius Ptolemy (ca. 100–165 CE). The “Little Astronomy” included works by a group of …

Exploring The Potential Of Strongly Coupled Lagrangian Data Assimilation In An Ocean–Atmosphere System, Luyu Sun, Amit Apte, Laura Slivinski, Elaine T. Spiller

Mathematical and Statistical Science Faculty Research and Publications

Precise measurements of ocean surface flow velocities are essential for refining forecasts in a coupled ocean–atmosphere system. While oceanic data are generally sparse, surface drifters present an opportunity by providing detailed and frequently observed sea surface currents, which are a critical component in the dynamics at air–sea interface. Such observations could potentially address the usual data gaps in a coupled ocean–atmosphere assimilation system. In this study, we investigate the implications of assimilating drifter data within a coupled system with intermediate complexity based on a quasigeostrophic model—Modular Arbitrary-Order Ocean–Atmosphere Model (MAOOAM)—using observing system simulation experiments (OSSEs). Two main strategies for assimilating …

Modelled Flooding Impacts On Lower Fish River Watershed, Sebastian Loschner

Shelby Hall Graduate Research Forum Posters

This study investigates the impacts of compound flooding in the Lower Fish River watershed, Baldwin County, Alabama, with a focus on the potential effects of sea level rise due to climate change. Coastal flooding, particularly in smaller watersheds, is a growing concern as it results from the interaction of multiple factors, including rainfall, tidal changes, and extreme weather events. Compound flooding, which involves multiple flood drivers, is expected to worsen with climate change, as increased precipitation and rising sea levels create heightened flood risks. However, existing research on compound flooding predominantly focuses on large-scale watersheds, leaving a knowledge gap in …

Using Machine Learning Models To Improve The Cyber Physical Security Of Drones, Sean Lee, Aviv Segev

Shelby Hall Graduate Research Forum Posters

This research proposes a new manner of implementing machine learning models such that, when applied on a drone, it will be able to accurately identify and maintain the authenticity of the entity sending the control data to the drone. To begin with, the drone will, for a pre-determined amount of signals received per unit time, determine the average signal strength (RSSI) of them and use that average to determine the approximate distance between the drone and the source of those signals. This single data point will be fed into a custom implementation of the SCluStream algorithm (a real-time clustering machine …