Digital Commons Network^™

Prune: A Patching Based Repair Framework For Certifiable And Privacy-Robust Unlearning Of Neural Networks, Xuran Li, Jingyi Wang, Xiaohan Yuan, Peixin Zhang

Research Collection School Of Computing and Information Systems

Machine unlearning has emerged as a key mechanism for enabling the “right to be forgotten” in neural network models, allowing the selective removal of specific training data upon request. Existing approaches typically rely on retraining models with the remaining data, which is computationally expensive and difficult to verify, especially when deployed models are distributed or resource-constrained. To address this challenge, our prior conference work introduced PRUNE, a patching-based framework that formulates unlearning as a neural network repair problem. PRUNE achieves targeted forgetting by learning lightweight patch networks that redirect model predictions on the data to be unlearned while preserving performance …

Neural Symphony Of Flow Experience: Evidence For High-Dimensional Metastable Dynamics, Abdelrahman B. M. Eldaly, Kris Zhangguang Kang, Fiona Fui-Hoon Nah, Leanne Lai-Hang Chan, Keng Siau, Xiao Fan Liu, Richard Huskey, Langtao Chen, Tejaswini Yelamanchili, Rene Weber

Research Collection School Of Computing and Information Systems

Flow, an optimal experience characterized by deep immersion and engagement in an activity, has been extensively studied in behavioral research. However, its neural dynamic mechanism remains poorly understood. In a within-subject video gaming experiment, we captured neural activity underlying flow, boredom, and anxiety using a 64-channel electroencephalogram (EEG) system. Compared to boredom and anxiety, flow exhibits the highest global functional connectivity, metastability, and dimensionality of dynamic functional connectivity patterns, suggesting that flow is a highly adaptable process that is supported by high-dimensional neural dynamics. Unlike previous studies that focused on identifying static or localized brain activity, we examine the neural …

Generalized Logit Adjustment: Improved Fine-Tuning By Mitigating Label Bias In Zero-Shot Vision Models, Beier Zhu, Qianru Sun, Xun Yang, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, fine-tuning and ensembling are also commonly adopted to better fit the downstream tasks. However, we argue that such prior work has overlooked the inherent biases in foundation models. Due to the highly imbalanced Web-scale training set, foundation models are inevitably skewed toward frequent semantics, and thus the subsequent fine-tuning or ensembling is still biased. In this study, we systematically examine the biases in foundation models and demonstrate the efficacy of our proposed Generalized …

Restoring Linguistic Grounding In Vla Models Via Train-Free Attention Recalibration, Ninghao Zhang, Bin Zhu, Shijie Zhou, Jingjing Chen

Research Collection School Of Computing and Information Systems

Vision-Language-Action (VLA) models enable robots to perform manipulation tasks directly from natural language instructions and are increasingly viewed as a foundation for generalist robotic policies. However, their reliability under Out-Of-Distribution (OOD) instructions remains underexplored. In this paper, we reveal a critical failure mode in which VLA policies continue executing visually plausible actions even when the language instruction contradicts the scene. We refer to this phenomenon as linguistic blindness, where VLA policies prioritize visual priors over instruction semantics during action generation. To systematically analyze this issue, we introduce ICBench, a diagnostic benchmark constructed from the LIBERO dataset that probes language–action coupling …

Facevalue: Exploring Real-Time Self-View Overlays To Prompt Meaning-Oriented Self-Awareness In Remote Meetings, Gun Woo (Warren) Park, Anthony Tang, Fanny Chevalier

Research Collection School Of Computing and Information Systems

In remote video meetings, visual non-verbal cues, such as facial expressions or head movements, are seen continuously but often only partially. This increases ambiguity compared to in-person settings and can cause misinterpretation or misalignment between intended and perceived meaning. Motivated by communication theories, we designed FaceValue, a technology probe that augments the self-view with private, real-time overlays. These overlays are subtle, suggestive prompts intended to help attendees reflect on how their cues might be interpreted by others. To invite personal interpretation, FaceValue avoids behavioral labeling and instead aims to support meaning-oriented self-awareness: recognizing when visible cues may unintentionally (mis)communicate intent. …

Towards More Inclusive Ai Systems In Cities, Siew Ying Shee, Orlando Woods

Research Collection School of Social Sciences

Artificial Intelligence (AI) is increasingly embedded in urban infrastructures and governance, shaping how people, spaces, and futures are classified, prioritised, and managed. Yet, most AI systems are developed within a narrow set of linguistic and geopolitical contexts and exported globally, embedding particular epistemic assumptions into diverse urban environments. Even where formal inclusion metrics are met, such asymmetries can render certain populations and realities less legible within algorithmic systems. Prevailing approaches in digital inclusion—centred on fairness metrics, representation, or access—presume technologies as politically inert and bounded. Yet, the adaptive and probabilistic behaviour of contemporary AI disrupts this premise, challenging the idea …

Investigating The Impact Of Outreach Programmes On Second Level Students In Formal And Informal Computer Science Education In Ireland, Karen Nolan

Doctoral

Computer Science (CS) education at second-level in Ireland has undergone significant development, including the introduction of the Leaving Certificate Computer Science (LCCS). However, the existing literature examined demonstrated that access to and participation in CS education is uneven, resulting in many students having limited exposure CS at second-level before making educational choices. At the same time, students who elect to study LCCS require appropriate support as they engage with programming and other aspects of a relatively new formal curriculum. This thesis investigates the function of school-based CS outreach in helping students at these various phases of their second-level CS education …

Learning 1-Bit Lidar-Based Localization With Auxiliary Objective, Kaijie Yin, Zhiyuan Zhang, Tian Gao, Wentao Zhu, Cheng-Zhong Xu, Hui Kong

Research Collection School Of Computing and Information Systems

6-DoF LiDAR-based localization is a fundamental capability for autonomous systems operating in large-scale outdoor environments. Many deep-learning-based localization methods have achieved promising performance so far. However, as one of the always-on modules competing for limited on-board computational resources, the localization module is expected to consume only a small portion of the overall compute budget. Most existing learning-based methods are still too heavy for this purpose. In contrast, binary neural networks (BNNs) offer an appealing solution, but the 1-bit compression causes severe information loss and performance drop. In this paper, we address this challenge by proposing Binarized LiDAR-based Localization (BiLoc), the …

Analysis Of The Throttle Settings Under Uncertain Information, Latafat Gardashova, Nihad Afandi

Chemical Technology, Control and Management

Although classical fuzzy logic controllers are capable of modelling non-linear control systems, they fail to consider the reliability of linguistic information, sensor measurements, and expert knowledge. In this paper, an intelligent controller based on the use of Z-numbers is developed for steam-turbine throttle control. Linguistic information and its confidence degree are considered simultaneously in such a controller. The temperature and pressure values are taken as input variables, while the throttle rotation is selected as the controller output variable. At first, the Z-number representation system is constructed to include the credibility of linguistic measurements and control rules. Then, a Mamdani Type-1 …

Guardians Of The Record (Cs2 Edition): Heaps, Queues, And A Scarce Oracle, Ilan Goodman

Generative AI Teaching Activities

Students defend Wikipedia from vandals with data structures instead of infrastructure: a sliding-window edit-velocity tracker (hash map of queues), a hand-built binary min-heap, and a budget-bounded top-K selection decide which few suspicious edits earn a question to an expensive, rate-limited Oracle — a stand-in for a real LLM.

Nonlinear System Identification Based On Fuzzy Radial Basis Neural Network With Multi-Connected Weight Connections, Kabul Khudaybergenov

Chemical Technology, Control and Management

This paper builds on our earlier radial basis function network with multiple connections (RBFMC) by placing it within a fuzzy inference framework for nonlinear system identification. The idea is inspired by the diversity of neurotransmitters found in biological neurons: instead of a single hidden-to-output weight, RBFMC gives each hidden unit a multi-dimensional connection whose components act as independent filters. Once fuzzy logic is added, each hidden neuron becomes a fuzzy rule, and its antecedent is built from several Gaussian membership functions, one per connection. The resulting Fuzzy RBFMC produces an interpretable, multi-filter description of local regions of the input space …

Guardians Of The Record: A Two-Tiered Streaming Cascade With Kafka, Flink, And A Real Llm, Ilan Goodman

Generative AI Teaching Activities

Students build a streaming vandalism detector for live Wikipedia edits in which a fast rule-based tier decides which few of ~1,500 edits per minute are worth escalating to a slow, rate-limited real LLM (Gemini) — confronting the cost, latency, and failure modes of putting AI inside a production data pipeline.

Artificial Intelligence And Social Equities: Navigating The Intersectionalities In A Digital Age (Editorial), Daisuke Akiba, Julie Albright

Publications and Research

This editorial article introduces and synthesizes the Special Issue, “Artificial intelligence and social equities: navigating the intersectionalities in a digital age,” which examines how AI systems intersect with race, ethnicity, and interconnected identity dimensions across global contexts. The eight contributions span healthcare, digital media, higher education, organizational communication, and speculative futures, addressing anti-racist psychiatric algorithms, AI-generated visual disinformation, epistemic injustice between the Global North and South, algorithmically mediated rural–urban divides, culturally untranslated technology transfer, accessibility auditing across the AI lifecycle, and the tension between mechanical objectivity and empathic understanding. Read together, they show that AI is neither inherently …

An Analysis Of The Effects And Implementations Of The Early Literacy Grant In Arizona, Alicia Severiano Perez

Mathematics, Statistics, and Computer Science Honors Projects

Over the years, states have implemented Science of Reading (SoR) frameworks to address low literacy levels. The Early Literacy Grant (ELG) in Arizona funds and supports such frameworks for schools serving low-income students. This paper is the first to explore the grant through interrupted time series modeling to evaluate effectiveness and text analysis to understand its implementation. We do not find clear evidence of positive effects caused by the grant, other than some cases, such as Yuma County. Schools typically allocate funds toward salaries and hiring instructors. These findings raise questions about whether its allocations should be closely monitored.

Machine Learning For Functional Outcome Prediction After Vestibular Schwannoma Surgery: A Systematic Review And Diagnostic Test Accuracy Meta-Analysis, Shiva Nischal, Shaan Patel, Musa China, Kush Kale, Yi Hein Chai, Santosh Guru, William Muirhead, Patrick Grover

Department of Neurosurgery Faculty Papers

PURPOSE: Machine learning (ML) models have been increasingly applied to predict postoperative facial nerve dysfunction and hearing preservation after vestibular schwannoma (VS) surgery. However, reported performance varies substantially, and the overall diagnostic accuracy and clinical reliability of these models remain uncertain. We conducted a systematic review and diagnostic test accuracy meta-analysis to characterise the current state and methodological readiness of ML-based prediction of these outcomes.

METHODS: PubMed, Embase, and CENTRAL were searched from inception to February 2026. Studies evaluating ML-based prediction of facial nerve function or hearing preservation following VS surgery were included. Diagnostic performance metrics were pooled using random-effects …

The Self-Aware Room: A Framework For Operational Self-Awareness In Evolvable Blended Environments, David B. Smith

Publications and Research

The Self-Aware Room (SAR) is a room-scale research environment developed within the larger Balanced Blended Space and Blended Reality Performance System research trajectory. Rather than treating the room as a conventional “smart” environment composed of fixed automation technologies, SAR approaches it as an evolvable blended environment made from physical, virtual, conceptual, sensory, computational, and performative relationships. Its defining feature is not any particular sensor, model, or output device, but the set of transformations through which physical activity becomes structured observation, bounded representation, interpreted state, governed decision, and mediated response.

This paper develops the conceptual and methodological foundations of SAR as …

Humanity’S Grandeur In The Balance: Theological Reflections On Magnifica Humanitas, William L. Portier

The Journal of Social Encounters

No abstract provided.

Designing Process-Focused Feedback For College Writers Using Genai, Beata Blood, Maissane Aik, Zoey Zaldivar

Discovery Day - Daytona Beach

As generative AI tools like ChatGPT become more common in higher education, writing instructors face the challenge of guiding students toward effective and ethical use, particularly in asynchronous environments where immediate feedback is limited. This presentation reports on an exploratory study that addresses this challenge by shifting attention from AI’s outputs to students’ moment-by-moment writing processes. Grounded in applied linguistics approaches to writing research and process-tracing methods, the project employed case studies with both expert and novice users of GenAI. Expert participants, including academics and industry professionals, completed writing tasks while integrating AI into their workflows. Their sessions were recorded …

Measuring The Tokenization Premium: A Cost Audit For Underserved Language Communities, Avijit Roy, Proma Roy, Hrishitva Patel

Publications and Research

Large language models are increasingly deployed as general-purpose educational and technical assistance systems, but their basic infrastructure does not treat languages equally. One underexamined source of disparity is tokenization: semantically equivalent content can require substantially different token counts across languages, affecting API cost, latency, and usable context length before a model is even invoked. We introduce the Tokenization Equity Audit (TEA), a reproducible benchmark for measuring tokenization premiums in technical tutoring content. TEA evaluates three widely used tokenizers, GPT-4o’s o200k base, Qwen2.5-7B, and Mistral-7B, on a 120-item Python debugging corpus translated from English into Bengali, Hindi, Arabic, Tamil, and Yoruba. …

Enabling Asl Digital Communication Under Poor Internet Access, Swann Thantsin

Student Theses

Video conferencing degrades asymmetrically. When bandwidth falls, a hearing caller loses picture quality and keeps the conversation; a deaf and hard of hearing signer, whose language is carried entirely in the visual modality, loses the conversation. This thesis asks whether signed video reduced to the rates at which commercial platforms fail can be reconstructed at the receiver well enough to keep signing legible. A twostage reduction pipeline crops to the signer and transmits the face and hands at higher fidelity than their surroundings, achieving a reduction of approximately 99%; reconstruction uses a recurrent bottleneck mixer architecture, trained both conventionally and …

Real Bullets, Plastic Guns: Evaluating The Strength Of 3-D Printed Gun Parts, Maria Latenia Mayol

Student Theses

Privately made firearms (PMFs), often referred to as “ghost guns,” are firearms manufactured or assembled by individuals rather than federally licensed manufacturers. Although the terms are frequently used interchangeably, “ghost gun” more specifically describes an unserialized firearm, whereas PMFs include a broader range of firearms produced through nontraditional manufacturing methods. PMFs may be entirely 3-D printed, assembled from partially completed firearm kits, or constructed by integrating additively manufactured components with commercially manufactured firearm parts. The increasing accessibility of additive manufacturing and widespread dissemination of computer-aided design files have raised concerns about concealment, regulation, and forensic evasion, particularly when factory-manufactured components …

Clinical Utility Of An Fda-Authorized Artificial Intelligence Imaging Platform In Interstitial Lung Disease Diagnosis, Arjun Prakash Tambe, Ryan Boente, Gautam George, Fayez Kheir, Omid Tahamtani Omran, Kavitha Selvan

Division of Pulmonary, Allergy, and Critical Care Medicine Faculty Papers

Background/Objectives: The diagnosis of interstitial lung disease (ILD) is challenging and frequently delayed. Clinically accessible and minimally invasive diagnostic tools are needed to expedite the diagnosis of ILD while minimizing risk to patients. Fibresolve is an imaging artificial intelligence (AI) tool recently approved by the Food and Drug Administration (FDA) for use in ILD diagnosis and made available to clinicians. The objective of this study was to describe its utility in clinical practice. Methods: We conducted a prospective, observational study of patients across the United States (US) in whom Fibresolve was utilized during routine clinical practice between July 2024 and …

Graph Perturbation Analysis For Subgraph Counting, Hanhua Xiao, Yuchen Li, Kyriakos Mouratidis

PhD Student’s Publications Collection

Subgraph counting, which involves determining the frequency of a query graph within a data graph, has numerous applications such as query optimization, fraud detection, and evaluating the expressiveness of graph neural networks. Despite its importance, there has been no systematic study on the impact of adversarial graph perturbations on subgraph counts. In this work, we examine the kSub problem, which aims to identify k edge additions that maximize the count of a query graph. We prove that kSub is intractable due to its NP-hardness, even for constant approximation. To address this, we relax the problem into a top-k selection, termed …

Differential Effects Of Generative Artificial Intelligence On Formative And Summative Assessment Performance: A Quasi-Experimental Longitudinal Study, Md Istiak Morsalin

Master's Theses

Generative artificial intelligence has unsettled a core assumption of course assessment: that scores on unsupervised work reflect what students can do unassisted. This study tests whether the widespread availability of ChatGPT altered student performance differently on formative versus summative assessments in Business Analytics and Foundations, a required undergraduate quantitative-methods course taught by one instructor across nine cohorts. In a quasi-experimental longitudinal design, the Fall~2022 cohort ($n = 90$), the last to finish before ChatGPT's public release, serves as a control against eight post-ChatGPT cohorts spanning Spring~2023 through Summer~2025 ($N = 646$). Outcomes were drawn from McGraw-Hill Connect records using matched …

Llm-As-A-Judge For Software Engineering: Literature Review, Vision, And The Road Ahead, Junda He, Jieke Shi, Terry Yue Zhuo, Christoph Treude, Jiamou Sun, Zhenchang Xing, Xiaoning Du, David Lo

Research Collection School Of Computing and Information Systems

The rapid integration of Large Language Models (LLMs) into software engineering (SE) has revolutionized tasks from code generation to program repair, producing a massive volume of software artifacts. This surge in automated creation has exposed a critical bottleneck: the lack of scalable and reliable methods to evaluate the quality of these outputs. Human evaluation, while effective, is very costly and time-consuming. Traditional automated metrics like BLEU rely on high-quality references and struggle to capture nuanced aspects of software quality, such as readability and usefulness. In response, the LLM-as-a-Judge paradigm, which employs LLMs for automated evaluation, has emerged. This approach leverages …

Success Of New Ideas In Online Platforms: An Idea Network Perspective, Yimei Zhou, Qian Tang, Vincent Z.W. Mack Mack, Shao Yi Liaw

Research Collection School Of Computing and Information Systems

On online platforms, new ideas often emerge by recombining existing ones within idea networks. Unlike traditional knowledge networks, idea networks represent curated, meaning-based associations among ideas, offering a distinct lens on recombination. Drawing upon a hypergraph perspective, we investigate how new idea success depends on their structural and content attributes, and how collaborative participation shapes these attributes. Using data from an ideation platform, we find that both structural embeddedness and bridging benefit new idea success. Content diversity has no direct effect, but it amplifies the benefits of bridging while constraining those of embeddedness. Both crowd contributions and ideator expertise strengthen …

Leading The Change: Staff-Driven Ai Transformation In Smu Libraries’ Collection Team, Siew Khim Lim, Fion Goh

Research Collection Library

No abstract provided.

Spring Ai 2026 Workshop And Speaker Series Report, Gregory Blike, Hannah (Nyingi) Brown, Dora (Dawn) Nguyen, Rami Huu Nguyen, Ajanee Igharo, Frayni Calderon, Moumita Saha, Chengjie Zheng

Paul English Applied Artificial Intelligence (AI) Institute Publications

The AI Workshop and Speaker Series was organized by the Student Advisory Council of the Paul English Applied Artificial Intelligence Institute at the University of Massachusetts Boston with the guidance of Distinguished Professor of Computer Science Wei Ding to create a practical and student-centered AI learning space. The Spring 2026 series included workshops on LinkedIn Optimization, Data Mining, GitHub, Prompt Engineering, Machine Learning of Structured Data, and Applied LLMs with Responsible AI Use in Research, while the broader speaker series introduced students to AI career development, generative AI and LLMs for cybersecurity, transportation security, political sciences, and AI in biomedicine. …

Modeling The Psychological And Technical Factors Influencing The Use Of Artificial Intelligence Tools Among Non-Native Arabic Learners: A Comparative Study In Egypt, Saudi Arabia, And Jordan., Mohammad Odeh, Alaa Al Din Musa, Ahmed Ragab Ali Ghalish, Montaser Adel Sayed Ahmed

All Works

This study aimed to develop a predictive longitudinal model of the psychological and technical factors influencing the use of artificial intelligence tools among non-native Arabic learners (international students) in three Arab countries: Egypt, the Kingdom of Saudi Arabia, and Jordan. The study adopted an extended Technology Acceptance Model (TAM) incorporating two psychological variables: trust in artificial intelligence and artificial intelligence anxiety. A quantitative longitudinal design with two time waves (T1 and T2) over a full academic semester was employed using Hierarchical Multiple Regression Analysis and PROCESS Macro for mediation. The sample consisted of 812 international students from public universities in …

Ai-Ready Libraries Require Ai-Ready Librarians: Building Organisational Capability For Digital Transformation, Salihin Mohammed Ali

Research Collection Library

Academic libraries worldwide are rapidly experimenting with artificial intelligence (AI) to enhance research, learning, discovery, operations, and user engagement. However, many institutions continue to approach AI adoption primarily through isolated pilots, individual experimentation, or technology-centric initiatives. While these efforts generate innovation, they often struggle to scale sustainably without corresponding organisational capability development. This presentation argues that AI-ready libraries require AI-ready librarians and proposes an organisational capability approach for sustainable AI transformation in academic libraries. Drawing from the development of a library-wide AI strategy plans at Singapore Management University, the presentation explores how AI capability-building can be operationalised across diverse functional …