Digital Commons Network^™

When Politics Meets Digital Assets: Gender Identity Salience And Nft Pricing After Roe V. Wade, Xiang Liu, Yao Zhao, Ping Fan Ke

Research Collection School Of Computing and Information Systems

Major sociopolitical events can reshape public attention toward identity-related issues, potentially influencing valuation patterns in digital markets where identity-related characteristics are embedded in digital assets. Using the overturning of Roe v. Wade as an exogenous policy shock, this paper examines how gender attributes represented in non-fungible token (NFT) avatars affect market outcomes. Using transaction data from six major avatar-based NFT collections traded on Etherscan in 2022, we apply a quasi-experimental design combining propensity score matching and a difference-in-differences model. The results indicate that the policy shock significantly increased the resale prices of NFTs representing female avatars. These findings suggest that …

Rode: Linear Rectified Mixture Of Diverse Experts For Food Large Multi-Modal Models, Pengkun Jiao, Xinlan Wu, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yu-Gang

Research Collection School Of Computing and Information Systems

Large Multi-modal Models (LMMs) have significantly advanced a variety of vision-language tasks. The scalability and availability of high-quality training data play a pivotal role in the success of LMMs. In the realm of food, while comprehensive food datasets such as Recipe1M offer an abundance of ingredient and recipe information, they often fall short of providing ample data for nutritional analysis. The Recipe1M+ dataset, despite offering a subset for nutritional evaluation, is limited in the scale and accuracy of nutrition information. To bridge this gap, we introduce Uni-Food, a unified food dataset that comprises over 100,000 images with various food labels, …

Benchmarking Gaslighting Negation Attacks Against Multimodal Large Language Models, Bin Zhu, Yinxuan Gui, Huiyan Qi, Jingjing Chen, Chong-Wah Ngo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Multimodal Large Language Models (MLLMs) have exhibited remarkable advancements in integrating different modalities, excelling in complex understanding and generation tasks. Despite their success, MLLMs remain vulnerable to conversational adversarial inputs. In this paper, we systematically study gaslighting negation attacks—a phenomenon where models, despite initially providing correct answers, are persuaded by user-provided negations to reverse their outputs, often fabricating justifications. We conduct extensive evaluations of state-of-the-art MLLMs across diverse benchmarks and observe substantial performance drops when negation is introduced. Notably, we introduce the first benchmark GaslightingBench, specifically designed to evaluate the vulnerability of MLLMs to negation arguments. GaslightingBench consists of multiple-choice …

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.

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 …

Language Embeddings Meet Shallow Autoencoders, Rodrigo Alves, Vojtěch Vančura, Pavel Kordík, Antoine Ledent

Research Collection School Of Computing and Information Systems

Shallow autoencoders are appealing recommenders due to their simplicity, scalability, and competitive retrieval quality, but they struggle in strict cold-start settings where new items have no interactions. We propose an inductive shallow autoencoder that leverages item side information (language embeddings) by fixing the decoder to item features and learning only an encoder in the same semantic space. To prevent trivial self-reconstruction without enforcing a hard zero diagonal, we introduce diagonal gating: a leave-one-item-out objective that blocks the self-copy shortcut only for the item being updated while retaining context from the rest of the user history. An alternating-style optimization trains the …

Hide-And-Sweep: Detecting Concealed Cameras Via Led Illumination Sweeps, Jonghyuk Yun, Jaeyoung Moon, Yunseo Park, Sean Rui Xiang Tan, Byunghyun Kim, Rajesh Krishna Balan, Jun Han

Research Collection School Of Computing and Information Systems

Hidden cameras have increasingly infiltrated hotel and Airbnb rooms, posing serious privacy risks. Detecting such cameras is challenging because they are visually inconspicuous and often embedded inside everyday objects. Even worse, existing handheld detectors are manual and also rely on single-angle illumination and hence suffer from high false-positive rates. We present SweepLED (pronounced "sweepled")1, a practical hidden camera detection system that operates on a commodity smartphone augmented with an unobtrusive LED-embedded case. SweepLED performs LED sweeping - a controlled sequence of multi-angle illumination - while the user simply holds the phone still by hand, enabling the camera to capture how …

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 …

Anatomical Domain Shifts: Test-Time Heterogeneous Adaptation For 3d Human Pose Prediction, Qiongjie Cui, Pan Zhou, Jingjing Chen, Na Zhao

Research Collection School Of Computing and Information Systems

The research frontier in human pose prediction (HPP) is advancing toward continual test-time adaptation (TTA), where models must self-adapt to dynamic test distributions. To date, the homeostatic continual TTA remains the sole viable solution, which isolates the model parameters and update domain-sensitive ones. Despite mitigating full-body domain gaps, human anatomical heterogeneity (domain shifts often localize to specific regions) is ignored. This anatomical-agnostic approach forces uniform parameter adaptation across kinematically distinct segments, causing: over-adaptation of stable regions and under-adaptation of shift-prone articulations. To address it, we introduce TT-HA, a novel Test-Time Heterogeneous Adaptation that implicitly estimates domain changes for anatomical segments, …

History To Future: Evolving Agent With Experience And Thought For Zero-Shot Vision-And-Language Navigation, Guangzhao Dai, Shuo Wang, Zihan Wang, Guo-Sen Xie, Yang Yang, Jinshan Pan, Qianru Sun, Xiangbo Shu

Research Collection School Of Computing and Information Systems

Vision-and-Language Navigation in Continuous Environment (VLN-CE) requires an agent to follow language instructions to navigate the target destination. With the advancement of large language models (LLMs), recent efforts have explored adapting them for zero-shot VLN-CE, offering a promising solution in addressing the drawbacks of poor generalization in the training-based paradigm. However, existing LLM-based works primarily perform naive reasoning for decision-making and lack feedback, e.g., reviewing historical errors and predicting future potentials. Consequently, it may suffer from continuous failure for those initial error tasks. In this paper, we rethink LLM-based zero-shot VLN-CE and propose a new paradigm, named EvoNav, to improve …

Task Complexity Matters: An Empirical Study Of Reasoning In Llms For Sentiment Analysis, Donghao Huang, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Large language models (LLMs) with reasoning capabilities have fueled a compelling narrative that reasoning universally improves performance across language tasks. We test this claim through a comprehensive evaluation of 504 configurations across seven model families—including adaptive, conditional, and reinforcement learning-based reasoning architectures—on sentiment analysis datasets of varying granularity (binary, five-class, and 27-class emotion). Our findings reveal that reasoning effectiveness is strongly task-dependent, challenging prevailing assumptions: (1) Reasoning shows task-complexity dependence—binary classification degrades up to -19.9 F1% points (pp), while 27-class emotion recognition gains up to  +16.0 pp; (2) Distilled reasoning variants underperform base models by 3–18 pp on simpler tasks, …

How Do Machine Learning Models Change?, Joel Castaño, Rafael Cabañas, Antonio Salmerón, David Lo, Silverio Martínez-Fernández

Research Collection School Of Computing and Information Systems

The proliferation of Machine Learning (ML) models and their open source implementations has transformed AI research and applications. Platforms like Hugging Face (HF) enable this evolving ecosystem, yet a large-scale longitudinal study of how these models change is lacking. This study addresses this gap by analyzing over 680,000 commits from 100,000 models and 2,251 releases from 202 of these models on HF using repository mining and longitudinal methods. We apply an extended ML change taxonomy to classify commits and use Bayesian networks to model temporal patterns in commit and release activities. Our findings show that commit activities align with established …

Esg Reporting Lifecycle Management With Large Language Models And Ai Agents, Thong Hoang, Mykhailo Klymenko, Xiwei Xu, Shidong Pan, Yi Ding, Xushuo Tang, Zhengyi Yang, Jieke Shi, David Lo

Research Collection School Of Computing and Information Systems

Environmental, Social, and Governance (ESG) standards have been increasingly adopted by organizations to demonstrate accountability towards ethical, social, and sustainability goals. However, generating ESG reports that align with these standards remains challenging due to unstructured data formats, inconsistent terminology, and complex requirements. Existing ESG lifecycles provide guidance for structuring ESG reports but lack the automation, adaptability, and continuous feedback mechanisms needed to address these challenges. To bridge this gap, we introduce an agentic ESG lifecycle framework that systematically integrates the ESG stages of identification, measurement, reporting, engagement, and improvement. In this framework, multiple AI agents extract ESG information, verify ESG …

Mri-Based Deep Learning Radiomics Model For Automated Classification Of Disc Degeneration In The Lumbar Spine, Shiv Patil, Om Gandhi, Mert Karabacak, Matthew Carr, Konstantinos Margetis

Student Papers, Posters & Projects

Disc degeneration in the lumbar spine is a major cause of low back pain (LBP). The accurate grading of disc degeneration on magnetic resonance imaging (MRI) is critical for clinical management and patient selection for spine surgery. This study aims to develop and evaluate machine learning (ML) models that combine features from deep learning (DL) and radiomics for the automated prediction of Pfirrmann grade (PG), a measure of disc degeneration, using multi-parametric lumbar spine MRI. Sagittal T1, T2, and T2 SPACE MRIs of 218 patients with LBP were acquired from the SPIDER dataset. For each intervertebral disc and available sequence, …

The Lorekeeper’S Trial: Teaching Ai Literacy Through Active Learning In The Library Classroom, Taylor Greene, Douglas R. Dechow

Library Articles and Research

How can librarians engage students in critical, hands-on learning about artificial intelligence within the limitations of a one-shot session? At Chapman University, librarians have developed an AI literacy session that integrates ethics and hands-on exploration into workshops and course-embedded sessions. This presentation highlights how to weave AI literacy into information literacy instruction, with a focus on a First-Year Foundations program.

Presenters will discuss their efforts to reach students, staff, and faculty through AI literacy initiatives across campus. They will also demonstrate how the Lorekeeper’s Trial—a research quest inspired by RPGs—transforms AI and information literacy concepts into collaborative challenges. Through a …

Transportation Deserts And Structural Mobility Access In New York City, John Cruz

Student Theses

This study examines structural mobility access across New York City census tracts by constructing a tract-level Mobility Access Index (MAI) that integrates employment accessibility, hospital accessibility, and first-mile subway walking burden using MTA GTFS transit data, NYC Taxi and Limousine Commission trip records, and US Census American Community Survey demographic estimates. Three OLS regression models, supplemented by Lasso, Elastic Net, and Random Forest specifications, test whether structural access gaps are associated with short-distance connector trip intensity and per-worker connector cost burden. Results show that MAI varies substantially across tracts, with high access concentrated in Manhattan and along major subway corridors. …

Forecasting Interborough Express Ridership Using Network-Based Station Typologies And Direct Demand Models, Fomba Kassoh

Student Theses

Forecasting ridership for new transit infrastructure is difficult in the absence of observed outcomes, particularly under domain shift between an existing system and a proposed corridor. This study develops a station-level direct demand modeling (DDM) framework to forecast average weekday ridership for the proposed Interborough Express (IBX) in New York City — a 14-mile circumferential rapid transit corridor connecting Brooklyn and Queens. The approach pairs unsupervised learning with supervised estimation in a common feature space defined by transit service, accessibility, and built-environment characteristics. K-means clustering identifies latent station typologies (node–place regimes), and IBX stations are projected into this topology to …

Panda-Plus-Bench: A Clinical Benchmark For Evaluating The Robustness Of Ai Foundation Models In Prostate Cancer Diagnosis, Joshua L. Ebbert, Dennis Della Corte

Faculty Publications

Artificial intelligence foundation models are increasingly deployed for prostate cancer Gleason grading, where GP3/GP4 distinction directly impacts treatment decisions (active surveillance vs. intervention). However, these models may achieve high validation accuracy by learning specimen-specific artifacts rather than generalizable biological features, limiting real-world clinical utility. We introduce PANDA-PLUS-Bench, a curated benchmark dataset derived from expertly annotated prostate biopsies designed specifically to quantify this failure mode. The benchmark comprises nine carefully selected whole slide images from nine unique patients containing diverse Gleason patterns, with non-overlapping tissue patches extracted at both 512 × 512 and 224 × 224-pixel resolutions across eight augmentation conditions. …

Ai-Infused Writing-Intensive Problems For Introduction To Programming In C++, Esma Yildirim

Open Educational Resources

This exercise book uses Writing-Intensive (WI) pedagogy in an introductory programming course setting, because I believe WI can help students engage in deeper analysis of programming problems while strengthening their critical and analytical thinking skills. In computer science, a single problem can often be solved using multiple algorithms, designs, and implementation strategies. Exploratory thinking and reflective writing can improve students’ ability not only to read and write computer programs, but also to evaluate the efficiency, readability, and maintainability of algorithms and code. Students must learn not only how to design solutions, but also how to compare alternatives and determine the …

Origin And Age Of Fluvioglacial Sediments On Staten Island Ny And Implications For Meltwater Flow, Jane L. Alexander, Victoria Rivelli, Sean T. Thatcher

Publications and Research

In the northeastern United States, sediments related to the expansion and contraction of the Laurentide ice sheet have been extensively mapped throughout New England, as well as in New Jersey and on Long Island. However, linking these deposits around New York City is challenging due to the extensive urbanization. Staten Island is less developed than the other boroughs of New York City, however outcrops of rock and surface sediment are limited, making interpretation of its geologic history challenging. When small areas of sediment are temporarily exposed, they can be used to improve our understanding of sediment erosion and deposition over …

Development Path And Prospects Of Technologies For Detecting Hidden Hazards In Coalfield Fire Zones, Deng Jun, Wang Jinrui, Ren Shuaijing, Song Zeyang, Wang Caiping, Li Yaqing, Lu Junhui, Qu Gaoyang

Coal Geology & Exploration

Background Hidden hazards in coalfield fire zones are characterized by limited detectability, rapid evolution, and multi-hazard coupling, posing major challenges to the safe coal mining and related ecological restoration. Methods This study aims to achieve the fine-scale identification and risk control of hidden hazards in coalfield fire zones. Based on a systematic review of the genetic mechanisms and spatial distribution patterns of coalfield fire zones, this study summarizes the characteristics of three primary fire zone types: outcrop/surface fire zones, shallowly buried fire zones, and deeply buried underground burnt-out areas and fire zones within old coal pits. Multi-dimensional hazards caused by …

Bridging Images And Language In Radiology: A Comprehensive Prisma Systematic Review Of Transformer Vision-Language Models And Clinical Readiness, Mohammad T. Khasawneh Dr., Sadaf Tabatabaee

Systems Science and Industrial Engineering Student Scholarship

Transformer vision-language models (VLMs) promise end-to-end automation of radiology reporting and related multimodal tasks. However, evidence remains fragmented across datasets, architectures, evaluation practices, and levels of clinical validation, limiting fair comparison and safe translation into practice. Following PRISMA 2020/PRISMA-S, search engines including PubMed, IEEE Xplore, Web of Science, and Google Scholar were systematically searched for peer-reviewed, English-language studies published between 2019 and 2025 that used paired radiology images and free-text reports. Dual reviewers screened records and extracted data using a locked schema covering datasets, modalities, architectures, training objectives, evaluation metrics, and indicators of clinical readiness. Free-text model descriptions were normalized …

Productive Armature, Gabriel Ofem Peter

Masters Theses

What if water was all you had, what if your only source of survival was a body of water? I shudder to think that some people get to be put in this situation in the world we live in. As I understand the importance of water to survival, it is obvious that water can be the only lifeline of survival for a community. This is the experience for residents of Makoko, Lagos. Their survival depends on the Lagos Lagoon, a large body of water flowing in from the Atlantic Ocean. This research looks beyond the surface of what this community …

Frictional Intelligence, Posheng Cheng

Masters Theses

This is an experimental interaction design project that challenges anthropomorphism in human-computer interaction. In particular, the recent advancement of artificial intelligence technologies like Large Language Models has taken anthropomorphism to new heights. The conversational chatbot interface of AI prioritizes mimicking an inherently human communication medium to maximize human-likeness. However, anthropomorphism has several downsides. Conversational interfaces obscure the limitations and the tangible cost of the technology. They also imply fictional moral status and human-level cognitive capabilities, which means general public sentiment focuses on the ``overhyped'' excitement and fear rather than on other socio-ethical and capacity questions that are far more urgent …

Labor Market Responses To Ai: Measuring Wage Effects Across U.S. Occupations, Kaitlin Pham, Karla Rodriguez

Undergraduate Economics Working Paper Series

Artificial intelligence (AI) is rapidly changing economies around the world, with some experts predicting an impact greater than the Industrial Revolution. As AI becomes more common in daily life and business, questions have grown about how it might affect jobs, wages, and inequality. The rise of automation and highly capable AI models has made people wonder which occupations will benefit and which might be at risk. This study looks at how exposure to AI technologies affects wage trajectories in the United States. Using occupational-level data from O*NET and the U.S. Bureau of Labor Statistics, we build an AI exposure index …

Arylation Of Nitrogen, Oxygen And Carbon Nucleophiles By Aryl(Tmp)Iodonium Salts, Joseph Jordan Hatton

Dissertations and Theses

Substituted aromatic rings are present in industry in a plethora of organic molecules such as pharmaceuticals, agrochemicals, materials and beyond. Therefore, methods for broadly installing aryl rings into other compounds to create substituted aromatic rings are valuable to many organic chemists. Historically these transformations are achieved through methods such as nucleophilic aromatic substitution and metal catalyzed cross-coupling. Nucleophilic aromatic substitution is a user-friendly method in this space but is limited by reliance on specific electronics. Metal catalyzed cross-coupling reduced the dependence on electronics in this space, but metals are generally unattractive reagents due to high costs, toxicity and challenges with …

Multi-Level Variable Selection Using A Bart-Enhanced Mixed-Effects Framework, Keming Zhang, Yaoyao Li, Jungang Zou, Sijian Wang, Bernadette A. Fausto, Liangyuan Hu

College of Health Professions Faculty Papers

Selecting important individual- and cluster-level predictors has become increasingly critical in healthcare research, where data often exhibit hierarchical structures due to collection from multiple clusters. Mixed-effects models, which account for within-cluster correlation and between-cluster heterogeneity, are a natural approach for multilevel variable selection. However, currently available variable selection methods for multilevel data are predominantly based on mixed-effects models that impose restrictive parametric assumptions, potentially limiting their utility when the underlying relationships are nonlinear or involve interactions. While nonparametric methods have shown promise for variable selection in non-clustered data, they have been much less studied in the multilevel setting. Moreover, nonparametric …

Real-Time Instruction Internalization For Large Language Models, Brenden Smith

Theses and Dissertations

For the end user, Large Language Models (LLMs) are programs that process natural language inputs into natural language outputs. In popular usage, this tends to take the form of conversation: a user asks a question, provides information, or gives instructions, and the LLM (hopefully) replies in a manner we would expect of an informed and compliant person. While convenient and intuitive for users, this natural conversational format encourages the misconception that LLMs are learning from conversations, when they do not. This work presents the benefits and practicality of a language model paradigm that meets this user expectation -- that is, …

Improving Explainability And Interpretability Of Neural Networks Via Hyperparameter-Extended Influence Functions, William Breslin

Dissertations and Theses

Understanding how model predictions and training outcomes vary with changes in data, features, and modeling choices is central to explainable artificial intelligence. This dissertation introduces a unified framework for explainability by generalizing classical influence functions to encompass user-defined hyperparameters embedded in the training loss, model architecture, or data representation. By extending influence functions in this way, the framework broadens their applicability and integrates multiple explainability techniques into a single, coherent approach. It provides a common mathematical foundation linking data impact, feature importance, and model design analysis, and supports a broad class of additional explainability analyses beyond these settings. The demonstrated …

Geometric Structure In High-Dimensional Representations: Theory And Applications To Language, Jiayi Chen

Dartmouth College Ph.D Dissertations

This thesis develops a geometric perspective on high-dimensional representations, motivated by applications to language. Rather than treating representations solely as inputs to predictive models, we view them as structured objects whose geometry encodes meaningful information. In particular, we argue that such representations exhibit organization at multiple scales: at a global level, metric and clustering structure capture relationships such as genre, authorship, and discourse; at a local level, geometric quantities such as intrinsic dimension and curvature describe how these relationships vary across the space.

To study these phenomena, we combine empirical analysis with theoretical development. On the empirical side, we examine …