Computer Sciences Commons^™

Agile In The Age Of Ai: Considerations And Improvements For Streamlining Developer Workflows, Stephen Feng

University Honors Theses

This paper examines the integration of AI language models into Agile developer workflows during a six-month software development project. Using the development of SagacityWall, a mindfulness-based social media application built by a team of eight undergraduates, it identifies three key areas in Agile processes where AI provided meaningful leverage: translating business requirements into actionable developer work tickets, accelerating framework research and technology stack decisions, and reducing onboarding friction through AI-assisted code scaffolding and Behavior-Driven Development story formatting. The study finds that AI meaningfully boosted productivity across these stages – not by replacing developer judgment, but by reducing overhead at each …

Legal Ethics Of Ai Snake Oil: Navigating The Hype, Harm, And Hope Of Legal Ai, Drew Simshaw

Michigan Law Review

A review of AI Snake Oil.By Arvind Narayanan and Sayash Kapoor.

Scaling Up Multi-Agent Reinforcement Learning For Large Agent Teams And Long-Horizon Tasks: A Survey, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Multi-agent reinforcement learning (MARL) empowers multiple autonomous agents to acquire effective policies for collaborative problem-solving. Over the last decade, MARL has seen significant advancements, with numerous algorithms achieving impressive performance across various benchmarks and real-world applications. Nevertheless, the scalability of multi-agent systems, in terms of the number of agents and the length of the task horizon, remains a critical consideration for applying MARL methods to complex problem-solving. Given that a dedicated review of the existing approaches and challenges in scaling up multi-agent systems remains largely absent, this survey aims to bridge this gap by delivering a comprehensive review of MARL …

“Grandpa, Can You Speak Nicer?”: Envisioned Chatbot Roles And Design Tensions In Intergenerational Communication Conflicts, Tianyi Zhang, Emran Bin Elias Poh, Yueyue Hou, Yi-Chieh Lee, Renwen Zhang, Jiannan Li, Anthony Tang

Research Collection School Of Computing and Information Systems

Intergenerational conversations often break down when differences in tone, language, or expectations lead participants to feel dismissed or misunderstood. In this work, we explore how people envision AI-driven chatbot interventions for addressing communication problems in text-based intergenerational family chat. We conducted a scenario-based design interview with 10 pairs of family members from different generations, in which participants designed chatbot interventions that varied in intervention target and timing. Our findings show that participants expect chatbots to perform multiple themes of intervention, including mediating understanding, providing emotional support, offering evaluative commentary, and guiding interaction through behavioral suggestions. These expectations varied systematically across …

The Stars Align: Modeling User Rating Calibration With Sparse Semantic Review Features, Rodrigo Alves, Antoine Ledent

Research Collection School Of Computing and Information Systems

User ratings are often treated as comparable across users, although identical scores may reflect different experiences. We study whether ratings can be viewed as user-specific discretizations of a shared semantic continuum derived from review text. Our method maps reviews into sparse semantic features with a sparse autoencoder and learns user-specific filters for each rating level. On Amazon Electronics, the learned embeddings align along a shared low-dimensional rating axis. Users differ mainly in how they anchor and partition this continuum, while preserving its overall ordinal structure. These findings support a semantic view of calibration beyond scalar bias correction.

“From Remembering To Shaping”: Narrating Shared Experiences By Co-Designing Cultural Heritage Artifacts In Collaborative Vr, Yushang Yang, Fanxu Meng, Fiona Fui-Hoon Nah, L. C. Ray

Research Collection School Of Computing and Information Systems

The ways people remember and recall places reveal an invisible aspect of cultural heritage (CH), reflecting how individuals and communities relate to these places. Heritage is communal, emerging through collaboratively constructed narratives rather than individual records. To probe how people may share collective memories, we designed an immersive two-person workflow for collaboratively co-designing 3D artifacts and environments in virtual heritage locations, using Generative AI (GenAI) to instantiate these intangible memories. Observations of the co-creation process revealed that participants merged prompts and model placements when negotiating different perspectives. They used spatial operations to compose scenes, and also to express personal and …

Not Too Early, Not All At Once: Design Tensions In Ai-Mediated Self-Disclosure In Online Dating, Pei-Hua Tsai, Tianyi Zhang, Emran Bin Elias Poh, Anthony Tang, Yung-Ju Chang

Research Collection School Of Computing and Information Systems

Online dating relies on self-disclosure, yet initial conversations are fragile: users must navigate uncertainty around timing, boundaries, and reciprocity with little shared context. While advances in AI raise the possibility of mediating disclosure, how such support might reshape the experience of early-stage relational disclosure remains underexplored. We conducted 29 semi-structured interviews to examine how daters envision AI-mediated self-disclosure in online dating. Our findings surface recurring design tensions rather than simple opportunities or risks. Participants welcomed guidance that could pace disclosure, support reflection, and reduce social awkwardness, but stressed preserving agency and authorship. They valued interpretive assistance for sense-making of ambiguous …

Context Matters: Auditing Gender Bias In T2i Generation Through Risk-Tiered Use-Case Profiles, Jose Luis Luna Campoverde, Yankun Wu, Xiaofei Xie, Noa Garcia

Research Collection School Of Computing and Information Systems

Text-to-image (T2I) generative models are increasingly used to produce content for education, media, and public-facing communication, and are starting to be integrated into higher-impact pipelines. Since generated images tend to reinforce stereotypes, producing representational erasure via “default” depictions and shaping perceptions of who belongs in certain roles, a growing body of work has proposed metrics to quantify gender bias in T2I outputs. Yet existing evaluations remain fragmented. Metrics are often reported without a shared view of what they measure, what assumptions they entail, or how their results should be interpreted under different deployment contexts. This limits the usefulness of gender …

Rc-Nf: Robot-Conditioned Normalizing Flow For Real-Time Anomaly Detection In Robotic Manipulation, Shijie Zhou, Bin Zhu, Jiarui Yang, Xiangyu Zhao, Jingjing Chen, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Recent advances in Vision-Language-Action (VLA) models have enabled robots to execute increasingly complex tasks. However, VLA models trained through imitation learning struggle to operate reliably in dynamic environments and often fail under Out-of-Distribution (OOD) conditions. To address this issue, we propose Robot-Conditioned Normalizing Flow(RC-NF), a real-time monitoring model for robotic anomaly detection and intervention that ensures the robot's state and the object's motion trajectory align with the task. RC-NF decouples the processing of task-aware robot and object states within the normalizing flow. It requires only positive samples for unsupervised training and calculates accurate robotic anomaly scores during inference through the …

Navigating Oer Support Without Drowning In Ai, Lydia Burrage-Goodwin, Christine Moynihan

Joseph P. Healey Library Publications

This was a presentation at the June 2026 Boston Library Consortium at Connecticut College.

UMB Healey Librarians Lydia Burrage-Goodwin and Christine Moynihan talk about what experiences they have had with faculty using OER and AI, which led them to develop ethics guidelines to support librarians who work with faculty authors. Attendees learned about creating AI use statements for OERs, using AI transparency logos, and applying open licenses to fully AI generated content as well as OER adaptations.

A Proactive Food Demand Forecasting-Inventory Management Approach Under Weather Disruptions, Asmaa Seyam, Sujith Samuel Mathew, May El Barachi, Jun Shen

All Works

Effective demand forecasting has become crucial to strengthening system resilience, reducing food waste, and achieving sustainability in food systems. Despite recent advances in leveraging machine learning for food demand forecasting, most existing models remain static and assume stable demand patterns, posing a challenge for adapting to demand changes during disruption events. This paper develops a proactive approach that leverages demand forecasting outputs and weather disruption flags to guide inventory replenishment, ensuring adaptability to varying demand conditions across three weather disruption events while reducing waste. This paper first uses a stacking model to predict next-day demand for a food retailer, leveraging …

The Association Between Ethical Ai Use And Well-Being Among Young Adults In The Uae: A Structural Equation Modeling Approach, Areej Elsayary, Zeina Hojeij, Lames Abdul Hadi

All Works

This study examines the association between ethical AI use and young people’s emotional, social, and psychological well-being in the United Arab Emirates (UAE), where the number of hours spent on GenAI serves as a moderator. Framed within the Theory of Planned Behavior and aligned with the Sustainable Development Goals (SDGs), particularly SDG 3 (Good Health and Well-being) and SDG 13 (Climate Action), this research examines how responsible digital engagement is associated with both individual mental health and broader digital sustainability. A Structural Equation Modeling approach assessed how ethical AI behaviors are associated with well-being. A total of 204 participants, predominantly …

Comparing The Sensitivity And Degree Of Boolean Functions Via The Hypercube, Anne-Caroline Rupp

University Honors Theses

This thesis studies three complexity measures of total Boolean functions f:{0,1}ⁿ → {0,1}: maximum sensitivity s(f), polynomial degree deg(f), and spectral sensitivity λ(f), where λ(f) is defined as the spectral norm of the adjacency matrix of the sensitivity graph. Building on the results of Aaronson et al., we examine the inequality chain √s(f) ≤ λ(f) ≤ deg(f) and investigate whether all three quantities can be simultaneously equal.

The first part of the thesis reverse engineers the equality cases of the two known inequalities to isolate necessary extremal conditions on both the Fourier structure of f and the local geometry …

Quantum And Conventional Informatics Studies Of Synthesis Energetics And Defect Formation In Nitride Crystal Epitaxy, Andrew Steven Messecar

Dissertations

Machine learning is a valuable approach for the processing and analysis of complex information. By estimating relationships from recorded data, machine learning methodologies can be effective strategies for pattern recognition, enabling investigations and technological applications based thereon. The potential for improved understanding of high-dimensional data has drawn interest towards machine learning from across the sciences, including the research and development of new and improved material systems. In the context of experimental materials research, much of the reported efforts to incorporate machine learning into conventional practice have been primarily focused on either the enhanced analysis of characterization experiment data or the …

When Saying "No" Is Not Enough: Cognitive-Action Decoupling And The Illusion Of Safety In Llm Agents, Shasha Yu

School of Professional Studies

Current safety evaluations of large language models (LLMs) predominantly rely on textual compliance, implicitly assuming that refusal-style responses correspond to safe behavior. This assumption becomes fragile when LLMs are embedded in agentic systems with the ability to execute state-changing actions. In this paper, we present an empirical critique of text-centric safety evaluation through an action-aware study of LLM agents under controlled conditions. Across multiple state-of-the-art models, we observe a recurring cognitive-action decoupling: agents generate policy-aligned refusal language while still producing unsafe tool-mediated action proposals. This produces an illusion of safety, where conversational audits indicate compliance even as operational risk persists. …

Trace: Temporal Rhetorical Analysis And Consistency Evaluation For Legislative Speech, David Hernandez

Master's Theses

Legislators frequently discuss the same policy issues across multiple hearings and legislative sessions, sometimes maintaining consistent positions and other times modifying or reframing their stance over time. Understanding how these positions evolve is important for analyzing political discourse and democratic accountability, yet identifying such shifts at scale remains difficult.

We introduce TRACE (Temporal Rhetorical Analysis and Consistency Evaluation), a system built on the Digital Democracy Database (DDDB) for detecting rhetorical inconsistency in California legislative hearing testimony. TRACE organizes utterances into speaker-anchored timelines indexed by bill and session, then applies hybrid semantic retrieval — combining dense BGE embeddings with BM25 lexical …

Daily Rainfall Forecasting Over West Bengal With Spatio-Temporal Graph Networks, Risheek Ghosh

Master’s Dissertations

Daily rainfall is hard to forecast where most days are dry, a few days are very wet, and almost all of the rain arrives in one season. This dissertation studies day-ahead rainfall forecasting over West Bengal, India, using models that learn from both the temporal and the spatial layout of measuring stations. We first build up a forecasting model in stages, from simple models that look at one station’s past to a graph-based model that links nearby stations, and we identify the strongest deterministic forecaster among them. We then ask whether the choice of input data changes the story, by …

Applications Of Prior And Novel Computational Tools In Mental Health Treatment, And Their Potential To Uncover The Explanatory Gap, Ambika Vyas

University Honors Theses

The explanatory gap is a widely discussed concept in scientific and philosophical literature. In neuroscience, the solution to the explanatory gap is highly sought out, but the general consensus is that it is unsolvable. Numerous articles discuss the explanatory gap alongside computational tools and how these tools could aid neuroscientists in uncovering the mental health explanatory gap. However, significant developments in machine learning have been made since 2020, coinciding with the rise in Large Language Models (LLMs). This thesis is a literature review on computational methods, tools, and devices developed and utilized by researchers to improve how mental health disorders …

Empirical Comparsion Of Traveling Salesperson Approximation Algorithms, Shayan Daijavad

Master's Theses

The traveling salesperson problem deals with optimizing the route a traveling sales- person might take to visit a set of places exactly once and return back to their starting point. The problem is NP-hard, and it is hard to approximate in general, but special cases have many approximation algorithms, which come with tradeoffs. In this thesis we compare the runtime, approximation ratio, and overall implementation complexity of two approximation algorithms for the Euclidean version of the problem, a classical 2-approximation algorithm and the multifragment heuristic. We run both algorithms on randomly generated point sets and real world data from TSPLIB. …

Political Inconsistency Detection Across Legislative Speech And Public Communications, Scott M. Pramuk

Master's Theses

Political actors communicate about legislation across multiple contexts, including committee hearings, recorded votes, and public-facing press releases. Differences between these forms of communication can provide useful signals for journalists and researchers seeking to understand how legislators present policy positions to different audiences.

This thesis extends the Digital Democracy Project, a legislative transparency initiative that provides access to California state legislative hearing transcripts, voting records, and related legislative data. Specifically, this work incorporates publicly accessible, legislator-authored news releases into the Digital Democracy Database and develops a pipeline for analyzing legislative communication across multiple sources. The system collects news releases from California …

Multimodal Machine Learning For Soil Burn Severity Mapping Across California Wildfires, Sanjana Checker

Master's Theses

Accurate mapping of soil burn severity (SBS) is critical for post-fire watershed management, erosion risk assessment, and ecological recovery planning, yet traditional field-based approaches remain costly, time-intensive, and spatially limited. This thesis presents a machine learning pipeline for wall-to-wall SBS classification across California wildfires using multi-sensor satellite imagery, terrain derivatives, and bioclimatic covariates. Field-collected SBS observations (n = 2,180) from 52 wildfires occur- ring between 2013 and 2025, sourced from the U.S. Forest Service and CAL FIRE, were used to train and evaluate multiple classification architectures within a Google Earth Engine and Google Cloud-based prediction framework. After upsampling the unburned …

Integer Quantization And Embedded Deployment Of Cnn Star Trackers For Cubesats, Meora R. Giusiano

Master's Theses

A star tracker determines spacecraft orientation by photographing the star field, detecting stars in the image, matching them against a catalog, and computing the rotation between observed and cataloged directions. Convolutional neural networks (CNNs) have been proposed as replacements for the detection and centroiding stage, offering improved sub-pixel accuracy and recovering faint stars that classical thresholds lose to stray light and sensor noise. The improvement comes at higher computational cost; the PolySat systemboard targeted in this work lacks the floating-point hardware these networks assume.

This thesis closes the gap between floating-point desktop evaluation and embedded integer deployment. Nine encoder-decoder CNN …

What Makes A Modern Attention Implementation?, Brian H. Slonim

Master's Theses

Since the seminal assertion by Vaswani et al. in 2017 that “Attention Is All You Need,” transformer models have risen to ubiquity due to their ability to learn extremely complex patterns from sequence data, culminating in the unprecedented generative capabilities of large language models. These models’ strength lies in their scale: hundreds of millions (e.g., BERT-LARGE) to billions or trillions of learned parameters. Running inference with these models, let alone training them, would be intractable without significant innovations in the hardware and software that support them. This need has driven an enormous demand for GPU compute and associated software ecosystems, …

Adversarial Robustness Of Perceptual Hashing Systems: A Unified Security Evaluation Framework, Avijit Roy

Student Theses

Social network platforms, child safety organizations, and image provenance systems use perceptual hashing to identify known child sexual abuse material (CSAM), support content moderation and reverse image search, and verify image integrity. Perceptual hashing works by producing similar fingerprints for visually similar images, even after common transformations such as compression, resizing, or minor brightness changes. This useful similarity-preserving property also creates an adversarial attack surface, as attackers can use AI-assisted or conventional image manipulation techniques to move a hash across a matching threshold while maintaining visual similarity, often without access to specialized hardware.

The security failures produced by adversarial attacks …

The Security Of Llm-Generated Code, Christopher Brian Gonzalez Ayala

Student Theses

The rapid adoption of Large Language Models (LLMs) in software development has transformed coding practices by enabling automated code generation, completion, and optimization. Despite these advantages, concerns persist regarding the security and reliability of LLM-generated code. This study presents a comprehensive evaluation of both the functional correctness and security of code produced by three prominent LLMs as of early 2026. A total of 4,800 code snippets were generated using 100 security-focused programming prompts derived from the OWASP Top 10:2025, translated across eight natural languages and two phrasing styles (literal and natural developer-oriented prompts). To assess performance, a multi-stage experimental framework …

Crab: A Novel Clustering Score Using Clustering With Rivals And Buddies For Unsupervised Learning, Allen Choi

Master's Theses

Unsupervised clustering algorithms today are used across a wide variety of fields such as biology, engineering, and industry in order to classify observations into groups where labels are not provided. This can provide important latent information regarding the observations within groups, as well as insight regarding the groups themselves. In order to judge the optimal number of clusters for an unsupervised clustering algorithm, many methods exist such as the Elbow Method and Silhouette Score; however, these methods come with drawbacks and are not necessarily flexible across many unsupervised methods. We present a novel clustering score framework relying on a resampling-based …

Inductive Biases In Field-Level Cosmological Inference From Galaxy Catalogs, James O'Connor Baldwin

Dissertations, Theses, and Capstone Projects

We perform field-level likelihood-free inference of the matter density parameter Ωm from simulated galaxy catalogs using machine learning models with differing inductive biases. Using features extracted from hydrodynamic simulations in the CAMELS suite, we investigate how both observable choice and model architecture govern the extraction of cosmological information. We consider galaxy positions and line-of-sight peculiar velocities, both separately and in combination, and compare permutation-invariant Deep Sets, implemented with either standard multilayer perceptrons (MLPs) or Kolmogorov–Arnold Networks (KANs), to graph neural networks (GNNs) implemented with MLPs, which explicitly encode spatial relations. We evaluate inference performance under both in-distribution and out-of-distribution (OOD) …

Integrating Multi-Scale And Multi-Filtration Topological Features For Medical Image Classification, Pengfei Gu, Huimin Li, Haoteng Tang, Dongkuan Xu, Erik Enriquez, Dongchul Kim, Bin Fu, Danny Z. Chen

Computer Science Faculty Publications

Modern deep neural networks have shown remarkable performance in medical image classification. However, such networks either emphasize pixel-intensity features instead of fundamental anatomical structures (e.g., those encoded by topological invariants), or they capture only simple topological features via single-parameter persistence. In this paper, we propose a new topology-guided classification framework that extracts multi-scale and multi-filtration persistent topological features and integrates them into vision classification backbones. For an input image, we first compute cubical persistence diagrams (PDs) across multiple image resolutions/scales. We then develop a "vineyard" algorithm that consolidates these PDs into a single, stable diagram capturing signatures at varying granularities, …

Towards Efficient Continual Learning: From Memory Optimization To Foundation Models, Zilin Luo

Dissertations and Theses Collection (Open Access)

Continual learning, also termed lifelong learning, enables machine learning models to incrementally acquire new knowledge while mitigating the degradation of previously learned information—a capability essential for adapting to dynamic, real-world data environments. This dissertation investigates the core challenges of continual learning and extends its application to enhancing training efficiency in the era of foundation models. The first part of this dissertation addresses the constraints of few-shot exemplar storage with a novel compression framework. While leveraging class activation maps to downsample non-discriminative pixels, we introduce an adaptive masking model, optimized through bilevel optimization, to store more exemplars efficiently. The second part …

Towards Auto-Evaluation For Large Language Models, Jiahao Ying

Dissertations and Theses Collection (Open Access)

The rapid advancement of large language models (LLMs) has created an urgent need for evaluation methodologies that are timely, scalable, reliable, and informative. Conventional evaluation benchmarks, although essential for measuring model capabilities and guiding model development, are often constructed and maintained through labor-intensive human annotation. As LLMs continue to improve through increases in model scale, training data, and computational resources, static benchmarks may quickly lose discriminative power. Moreover, the growing use of large and diverse training corpora increases the risk of benchmark leakage, which can inflate evaluation results and obscure the true capabilities of models. These challenges call for a …