Digital Commons Network^™

Structural Silence: When Ai Infrastructure Fails Speakers Of Underrepresented Languages, Avijit Roy, Proma Roy

Publications and Research

Artificial intelligence tools for education and language support are increasingly framed as scalable responses to access gaps in under-resourced communities. Yet the infrastructure underlying these tools—training corpora, tokenization schemes, evaluation benchmarks, and deployment architectures—encodes a set of assumptions that systematically disadvantages speakers of underrepresented languages before a single model is trained. This paper examines those assumptions through the lens of Bengali, one of the world’s most widely spoken languages with roughly 285 million speakers (Ethnologue, 2025; International Communication and Leadership School, 2026), and the structural barriers that emerge when attempting to build AI-assisted educational tools for Bengali-speaking learners in low-connectivity …

Watersmart Farms - Desalination: Community Desalination, Sharmina Begum, Wendell Ela, John K. Ruprecht

Natural resources commissioned reports

The Wheatbelt is a vast agricultural region in southwestern Western Australia, covering approximately 25 million hectares, of which 17 million are cleared. It is a key contributor to the state’s economy, supporting broadacre grain production, livestock (such as sheep, beef, and pigs) grazing, mixed farming, and numerous small rural communities. However, decades of extensive land clearing for agriculture have significantly altered the natural hydrological balance. These changes have disrupted local water cycles, increased recharge post-clearing, increased evaporation, and contributed to widespread soil salinity.

Compounding these land-use impacts, the region has also experienced a long-term drying trend due to climate change. …

Weakly Supervised Video Anomaly Detection And Localization With Spatio-Temporal Prompts, Peng Wu, Xuerong Zhou, Guansong Pang, Zhiwei Yang, Qingsen Yan, Peng Wang, Yanning Zhang

Research Collection School Of Computing and Information Systems

Current weakly supervised video anomaly detection (WSVAD) task aims to achieve frame-level anomalous event detection with only coarse video-level annotations available. Existing works typically involve extracting global features from full-resolution video frames and training frame-level classifiers to detect anomalies in the temporal dimension. However, most anomalous events tend to occur in localized spatial regions rather than the entire video frames, which implies existing frame-level feature based works may be misled by the dominant background information and lack the interpretation of the detected anomalies. To address this dilemma, this paper introduces a novel method called STPrompt that learns spatio-temporal prompt embeddings …

Portrait Shadow Removal Via Self-Exemplar Illumination Equalization, Qian Huang, Cheng Xu, Guiqing Li, Ziheng Wu, Shengxin Liu, Shengfeng He

Research Collection School Of Computing and Information Systems

We introduce the Self-Exemplar Illumination Equalization Network, designed specifically for effective portrait shadow removal. The core idea of our method is that partially shadowed portraits can find ideal exemplars within their non-shadowed facial regions. Rather than directly fusing two distinct classes of facial features, our approach utilizes non-shadowed regions as an illumination indicator to equalize the shadowed regions, generating deshadowed results without boundary-merging artifacts. Our network comprises cascaded Self-Exemplar Illumination Equalization Blocks (SExmBlock), each containing two modules: a self-exemplar feature matching module and a feature-level illumination rectification module. The former identifies and applies internal illumination exemplars to shadowed areas, producing …

Stacked From One: Multi-Scale Self-Injection For Context Window Extension, Wei Han, Pan Zhou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward solution, it incurs prohibitive data acquisition and computational costs. To address this challenge, we propose SHAREDLLM, a novel framework based on multi-grained context compression and query-aware information acquisition. SHAREDLLM comprises two stacked short-context LLMs: a lower model serving as a compressor and an upper model acting as a decoder. The lower model compresses long inputs into compact, multi-grained representations, which are then forwarded to the upper model for context-aware processing. …

Dragging With Geometry: From Pixels To Geometry-Guided Image Editing, Xinyu Pu, Hongsong Wang, Jie Gui, Pan Zhou

Research Collection School Of Computing and Information Systems

Interactive point-based image editing serves as a controllable editor, enabling precise and flexible manipulation of image content. However, most drag-based methods operate primarily on the 2D pixel plane with limited use of 3D cues. As a result, they often produce imprecise and inconsistent edits, particularly in geometry-intensive scenarios such as rotations and perspective transformations. To address these limitations, we propose a novel geometry-guided drag-based image editing method—GeoDrag, which addresses three key challenges: 1) incorporating 3D geometric cues into pixel-level editing, 2) mitigating discontinuities caused by geometry-only guidance, and 3) resolving conflicts arising from multi-point dragging. Built upon a unified displacement …

Where Did It Go Wrong? Attributing Undesirable Llm Behaviors Via Representation Gradient Tracing, Zhe Li, Wei Zhao, Yige Li, Jun Sun

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the root causes of these failures poses a critical challenge for AI safety. Existing attribution methods, particularly those based on parameter gradients, often fall short due to prohibitive noisy signals and computational complexity. In this work, we introduce a novel and efficient framework that diagnoses a range of undesirable LLM behaviors by analyzing representation and its gradients, which operates directly in the model's activation space to provide a semantically meaningful signal linking …

Propaganda Ai: An Analysis Of Semantic Divergence In Large Language Models, Nay Myat Min, Long H. Pham, Yige Li, Jun Sun

Research Collection School Of Computing and Information Systems

Large language models (LLMs) can exhibit concept-conditioned semantic divergence: common high-level cues (e.g., ideologies, public figures) elicit unusually uniform, stance-like responses that evade token-trigger audits. This behavior falls in a blind spot of current safety evaluations, yet carries major societal stakes, as such concept cues can steer content exposure at scale. We formalize this phenomenon and present RAVEN (Response Anomaly Vigilance), a black-box audit that flags cases where a model is simultaneously highly certain and atypical among peers by coupling semantic entropy over paraphrastic samples with cross-model disagreement. In a controlled LoRA fine-tuning study, we implant a concept-conditioned stance using …

Managing Reproducibility Debt In Scientific Software: A Practical Framework, Zara Hassan, Christoph Treude, Graham Williams, Michael Norrish, Alex Potanin

Research Collection School Of Computing and Information Systems

Scientific software includes end-user applications, modelling tools, research software for publications, and production systems for real users. It plays a key role across various scientific disciplines by enabling large-scale computation, simulation, and data analysis. Unlike commercial software, scientific software is often developed in dynamic research environments with limited engineering practices, documentation, or testing. This makes it fragile and difficult to reproduce results, even when code and data are available, conditions in which Reproducibility Debt (RpD) accumulates. This paper presents the Reproducibility Debt Management Framework (RpD-MF), which is grounded in evidence from a systematic literature review, practitioner interviews, and a global …

Llmqua: Practical Backdoor Injection On Large Language Model Quantization, Xiangxiang Chen, Peixin Zhang, Jun Sun, Jin Song Dong, Wenhai Wang, Jingyi Wang

Research Collection School Of Computing and Information Systems

Quantization is widely used to enable local deployment of large language models (LLMs) on resource-constrained devices. Recent work (e.g., QuRA) shows quantization can be exploited via rounding manipulation to implant backdoors. However, such an attack has been evaluated only on small models and does not directly apply to LLMs due to three key constraints: (1) limited poisoning data from small, task-agnostic calibration sets; (2) layer-wise quantization restricting adversarial access to global representations; and (3) lack of gradient access in quantization pipelines, blocking gradient-based attacks.We propose LLMQuA, a practical quantization-phase backdoor attack tailored to the LLM setting. LLMQuA (i) injects backdoors …

Be Responsible In Your Answers! Monitoring Out-Of-Domain Behaviors In Domain-Specific Llms, Boquan Li, Chenzhe Lou, Zhe Ren, Peixin Zhang, Zirui Fu, Jun Sun, Yaowen Zheng

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have accelerated the rapid development of chatbot web applications in various domains, such as coding, biomedicine and psychology. Compared to general LLMs like ChatGPT, domain-specific LLMs require a greater sense of responsibility. For instance, if a programming LLM casually answers medical or psychological questions, it not only misleads the public but also poses legal risks. This highlights new demands for monitoring and preventing such irresponsible behaviors. Existing efforts attempt to monitor LLMs from multiple aspects, such as lying, jailbreaks, and toxic content, while overlooking out-of-domain behaviors. In this work, we propose an innovative LLM domain monitoring …

Prompting Frameworks For Large Language Models: A Survey, Xiaoxia Liu, Jingyi Wang, Jun Sun, Xiaohan Yuan, Guoliang Dong, Peng Di, Wenhai Wang, Dongxia Wang

Research Collection School Of Computing and Information Systems

Since the launch of ChatGPT, a powerful AI Chatbot developed by OpenAI, large language models (LLMs) have made significant advancements in both academia and industry, bringing about a fundamental engineering paradigm shift in many areas. While LLMs are powerful, it is also crucial to best use their power where “prompt” plays a core role. However, the booming LLMs themselves, including excellent APIs like ChatGPT, have several inherent limitations: (1) temporal lag of training data, and (2) the lack of physical capabilities to perform external actions. Recently, we have observed the trend of utilizing prompt-based tools to better utilize the power …

Challenges In Synchronous And Remote Collaboration Around Visualization, Matthew Brehmer, Maxime Cordeil, Christophe Hurter, Takayuki Itoh, Wolfgang Büschel, Mahmood Jasim, Arnaud Prouzeau, David Saffo, Lyn Bartram, Sheelagh Carpendale, Chen Zhu-Tian, Andrew Cunningham, Anthony Tang, Samuel Huron, Masahiko Itoh, Arpit Joshi, Kiyoshi Kiyokawa, Hideaki Kuzuoka, Bongshin Lee, Guillermo Molina León

Research Collection School Of Computing and Information Systems

We characterize 16 challenges faced by those investigating and developing remote and synchronous collaborative experiences around visualization. Our work reflects the perspectives and prior research efforts of an international group of 29 experts from across human-computer interaction and visualization sub-communities. The challenges are anchored around five collaborative activities that exhibit a centrality of visualization and multimodal communication. These activities include exploratory data analysis, creative ideation, visualization-rich presentations, joint decision making grounded in data, and real-time data monitoring. The challenges also reflect the changing dynamics of these activities in the face of recent advances in extended reality (XR) and artificial intelligence …

Understanding Codebase Like A Professional! Human-Ai Collaboration For Code Comprehension, Jie Gao, Yue Xue, Xiaofei Xie, Junming Cao, Soemin Thant, Erika Lee, Bowen Xu

Research Collection School Of Computing and Information Systems

Understanding an unfamiliar codebase is an essential task for developers in various scenarios, such as during the onboarding process. Especially when the codebase is large and time is limited, achieving a decent level of comprehension remains challenging for both experienced and novice developers, even with the assistance of large language models (LLMs). Existing studies have shown that LLMs often fail to support users in understanding code structures or to provide user-centered, adaptive, and dynamic assistance in real-world settings.To address this, we propose learning from the perspective of a unique role, code auditors, whose work often requires them to quickly familiarize …

Ultra-High Vacuum Outgassing Characterization Of Thermally Processed Low-Carbon Steel For Advanced Particle Accelerator And Gravitational Wave Detector Applications, Aiman H. Al-Allaq

Mechanical & Aerospace Engineering Theses & Dissertations

This dissertation investigated AISI 1020 low-carbon steel as an alternative vacuum chamber material to conventional stainless steel for ultra-high vacuum (UHV) and extreme-high vacuum (XHV) applications. After a 400 °C/48 h bake, AISI 1020 tube chambers achieved a hydrogen outgassing rate of 2.4 × 10⁻¹⁶ Torr·L·s⁻¹·cm⁻², approximately 2,300 times lower than the prebaked 316L stainless-steel comparator, among the lowest hydrogen outgassing rates ever reported for an uncoated metallic vacuum chamber. Bare and magnetite-coated AISI 1020 chambers were then compared using throughput and rate-of-rise methods. The magnetite coating yielded 5× lower water outgassing at room temperature, but this advantage disappeared after …

Dissecting The Etiology Of Alcohol Use Disorder By An Integrative Heritable Component Approach, Ivy Garrenton

Computer Science Theses & Dissertations

Alcohol Use Disorder (AUD) is a pervasive condition characterized by complex interplay among genetic, phenotypic, and environmental factors. Although previous studies have identi fied genetic loci associated with alcohol consumption, these efforts have not captured the genetic heterogeneity and gene-environment interactions underlying AUD pathogenesis. To address this critical gap, we developed a novel statistical methodology that integrates phenotypic, genotypic, and environmental data through an environmentally modified Genetic Relationship Matrix (GRM) to derive AUD-related traits with enhanced heritability.

This approach demonstrated superior performance in both simulated and real-world datasets. Traits derived using the environmentally modified GRM exhibited significantly higher estimated heritability …

Ai-Assisted 3d Pre-Visualization: Streamlining Animatics For Filmmakers, Nishit Thapa

Honors Theses

Pre-visualization is a core part of film pre-production. Creators use it to test blocking, lighting, camera movement, and spatial relationships before committing to a shot. Despite this, three-dimensional pre-visualization remains out of reach for many entry-level filmmakers, as the software is expensive and takes substantial time to learn.

Recent AI developments have produced generative systems capable of creating highly re-alistic imagery and video from text prompts. These systems open new possibilities for visual sto-rytelling but are not built for the iterative, hands-on process that pre-visualization requires, where creators must adjust scene parameters, camera logic, and spatial configurations throughout.

This thesis …

A Comprehensive Calibration Framework For The Northwest River Forecast Center, Geoffrey Walters, Cameron Bracken, Brad Gillies, Leah Pope, Henry Pai, Sonali Chokshi, Victor Stegemiller, Stephen King, Julie Bracken, Taylor Dixon, Multiple Additional Authors

Mathematics and Statistics Faculty Publications and Presentations

We present a comprehensive framework developed by the Northwest River Forecast Center for calibrating hydrologically diverse basins. The framework includes models for snow, soil moisture, routing, channel loss, and consumptive use. Data inputs include a wide range of open-access datasets for meteorology, land use, topography, and land cover. The framework uses conceptual hydrologic models to handle basins with various hydrologic regimes including rain-driven and snowmelt-dominated basins. We also develop a flexible automatic calibration system that can handle numerous unobservable model parameters in a computationally efficient manner. A single-basin automatic calibration run can typically be completed on a modern laptop in …

Rethinking News Classification Through A Multi-Dimensional Framework, Luana De Jesus Ferreira

Honors Theses

This thesis proposes a multi-dimensional framework for news classification that evaluates articles across three independent dimensions: headline accuracy, language neutrality, and content reliability. These dimensions produce both a continuous reliability score and a five-tier interpretive scale, while additionally classifying articles by genre and topic. To operationalize this framework, a structured annotation protocol was developed and applied to a dataset of 373 news articles drawn from 79 outlets spanning a wide range of contemporary media ecosystem. A binary Logistic Regression classifier trained on the ISOT Fake News Dataset was then evaluated against this dataset to examine how a model trained on …

Examining Marine Fungal Nitrous Oxide Production, Qintiantian Nong

Theses and Dissertations

Nitrous oxide (N2O), a potent greenhouse gas, can be produced by microorganisms inhabiting marine environments. While bacterial denitrification is a major source of N2O, the role of marine fungi in this process remains poorly constrained. This thesis investigates the contribution of marine fungi to N2O production from salt marsh sediments, while also isolating new N2O-producing marine fungi and advancing methodological approaches for quantifying denitrification. First, we conducted experiments to quantify the fungal contribution to N2O production using salt and brackish marsh sediments collected from the North Inlet–Winyah Bay National Estuarine Research Reserve in South Carolina during the summer and winter …

Exploring The Efficiency Of Logistic Models With Opt-Out Designs In Discrete Choice Experiment And Their Applications, Dai Fang

Theses and Dissertations

A discrete choice experiment is usually conducted in economics background to measure how consumers would like to trade off attributes of a product, service, or policy. In this experiment, respondents are provided different hypothetical combinations of varied components by using an experimental design such as the full factorial design, which fully represents the all combinations of attributes and levels. The mathematical background of a discrete choice experiments is based random utility theory, in which either positive or negative values are given each characteristic and the weighted sum values of each choice given in the experiment will be compared. This experiment …

Evidence Of Metal-Microcystin Complexation And Its Potential Role In Environmental Fate, Ashley Marie Womer

Theses and Dissertations

Microcystins that enter freshwater systems pose a threat to human health therefore their fate and transport throughout the water column have been intensively studied. While sediment has been regarded as an environmental fate for microcystin (MC), less is known about the molecular mechanisms by which microcystin interacts with the sediment and/or the thermodynamic stability of these interactions. While microcystin has a half-life in lake water on the order of weeks, microcystin adsorbed to sediment can be detected hundreds of years later1-2. Microcystin has been desorbed from these sediments with various EDTA solutions, therefore, work is presented to support the hypothesis …

Raman Spectroscopy Of Biological Molecules And Inorganic Compounds, Jasmine Ervin Gardner

Theses and Dissertations

This dissertation describes the use of multiple Raman spectroscopic techniques for the detection and characterization of non-hazardous organic and inorganic compounds. The first two applications involve the use of Raman and surface enhanced Raman spectroscopy to thoroughly analyze autoinducers (AI) produced by gram negative bacteria. The second set of applications involves the use of anti-stokes Raman and resonance Raman spectroscopy to remotely detect inorganic compounds at distances of up to 12 meters away.

This work describes the use of Raman spectroscopy for the characterization and discrimination of signaling molecules used in bacterial communication. Our initial work shows the potential of …

Quantifying And Characterizing Microplastics In North Inlet And Winyah Bay Estuaries, Sc, Emily Grace Contract

Theses and Dissertations

Microplastics (1 μm to 5 mm) accumulate in the bodies of marine organisms and negatively impact their health. Microplastics have also been linked to birth defects, endocrine disruption, and cancer in humans. This study quantified, characterized, and compared microplastics in a protected estuary (North Inlet Estuary, South Carolina) and an estuary impacted by anthropogenic activities (Winyah Bay, South Carolina). Water samples were taken from three sites in each estuary from February 2025 to December 2025. The samples were digested, filtered, then examined visually for microplastics. Plastic particles were extracted and analyzed by Raman microscopy to obtain polymer content. Results indicate …

Conservation Communication In Web 2.0: A Mixed Methods Analysis Of Alveus Sanctuary's Strategies On Twitch.Tv, Hope Denison

Senior Theses

This thesis examines how environmental creators can effectively transmit conservation messages in the evolving Web 2.0 media environment. The case of Alveus Sanctuary, a virtual sanctuary and education center on Twitch.TV, is used to explore the strategies currently used to engage audiences and raise ecological awareness online. Thematic analysis of interviews with the sanctuary’s founder revealed that Alveus combines traditional environmental education with an influencer business model to engage online audiences, leveraging parasocial behavior, interactivity, and collaboration to garner support. A quantitative content analysis of social media posts revealed that these strategies effectively induce parasocial engagement in online spaces. These …

Evaluation Of Seal!Nd: School Year 2024-2025, Shawnda Schroeder, Rashid Ahmad

Indigenous Health Faculty Publications

Dr. Schroeder and Rashid worked with the team at the Oral Health Program to collect data on the clinical reach of the School-based Sealant program (SEAL!ND), the referral practices, dental sealant cost savings, and perceptions of school personnel regarding their experiences with the program. SEAL!ND continues to make a measurable difference in improving children’s oral health by increasing access to preventive care, reducing barriers for families, and supporting schools in meeting the needs of their students. The program’s impact is reflected not only in the thousands of services provided each year, but also in the strong satisfaction and gratitude expressed …

Software Engineering In The Age Of Coding Agents: Failure Modes And Rejection Patterns, Mahd Mohd Hindi

Thesis/ Dissertation Defenses

This thesis investigates the real-world behavior of LLM-driven coding agents that generate code changes and submit pull requests (PRs) to public software repositories. As these tools evolve from autocomplete-style assistants into more autonomous agents, their contributions increasingly interact with socio-technical review processes (human reviewers, bots, CI/CD gates, and project norms). This thesis focuses on understanding why agent-generated PRs are accepted or rejected and what these outcomes reveal about current agent limitations in practical development workflows. The main objective of this thesis is to systematically characterize rejection patterns and failure modes of agent-generated pull requests in real repositories. Specifically, the thesis …

Software Engineering In The Age Of Coding Agents: Failure Modes And Rejection Patterns, Mahd Mohd Taysir Hindi

Thesis/ Dissertation Defenses

This thesis investigates the real-world behavior of LLM-driven coding agents that generate code changes and submit pull requests (PRs) to public software repositories. As these tools evolve from autocomplete-style assistants into more autonomous agents, their contributions increasingly interact with socio-technical review processes (human reviewers, bots, CI/CD gates, and project norms). This thesis focuses on understanding why agent-generated PRs are accepted or rejected and what these outcomes reveal about current agent limitations in practical development workflows. The main objective of this thesis is to systematically characterize rejection patterns and failure modes of agent-generated pull requests in real repositories. Specifically, the thesis …

Employing Effective Solution Methods For Caputo-Based Sequential Fractional Models, Eman A. A. Ziada, Mohamed F. Abouelenein, Hijaz Ahmad, Monica Botros

Mathematical Modelling and Numerical Simulation with Applications

This paper investigates a class of nonlinear sequential singular fractional differential equations (FDEs) involving Caputo derivatives. This type of equation has several key advantages that enhance its value, such as capturing memory and hereditary effects. Viscoelastic materials and anomalous diffusion, as well as biological systems, can take advantage of this feature. In addition, fractional derivatives possess a sequential structure that enables the implementation of multiscale processes and hierarchical memory responses. Moreover, it provides an effective and flexible framework for solving differential equations compared to classical differential equations. It can therefore be used to model complex systems in physics, biology, and …

Optimal Control Strategies For Infectious Diseases: A Numerical Simulation Approach, M. Abu Salek, Jannatun Nayeem, Romana Yesmin, M. Haider Ali Biswas, M. Humayun Kabir

Mathematical Modelling and Numerical Simulation with Applications

Various infectious diseases, such as Tuberculosis and Hepatitis B virus (HBV), caused by Mycobacterium bacteria and hepatitis B virus, respectively, pose serious threats worldwide. This paper examines the spread of these diseases using a mathematical model that incorporates control measures, including vaccination and awareness programs. We use a system of differential equations with control variables and apply Pontryagin's principle to determine optimal control strategies. The stability of the Disease Free Equilibrium (DFE) has been analysed and demonstrated to be both locally and globally asymptotically stable when the basic reproduction number remains below unity, thereby ensuring disease elimination. Furthermore, the Endemic …