Digital Commons Network^™

Learning-Based Graph Shrinking For Quantum Optimization Of Constrained Combinatorial Problems, Monit Sharma, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Graph shrinking has recently emerged as a powerful preprocessing technique for hybrid classical–quantum optimization, enabling variable and constraint reduction before quantum solving. Conventional approaches rely on Semi-Definite Programming (SDP) relaxations to compute vertex correlations, but these methods suffer from high computational overhead, instance-specific tuning, and limited generalizability. In this work, we replace the handcrafted SDP correlation stage with a reinforcement learning (RL) based correlation estimator, trained to predict merge quality directly from graph structure. We reformulate the graph shrinking process as a Markov Decision Process (MDP), design a Graph Neural Network (GNN) policy to guide vertex merging, and integrate the …

Hybrid Learning And Optimization Methods For Solving Capacitated Vehicle Routing Problem, Monit Sharma, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We propose a hybrid quantum–classical framework for the Capacitated Vehicle Routing Problem (CVRP) that integrates the Augmented Lagrangian Method (ALM) with deep reinforcement learning (RL). Directly solving CVRP via Variational Quantum Eigensolver (VQE) requires a slack-based QUBO formulation, where converting inequalities to equalities greatly increases the qubit count. To circumvent this, we employ an ALM-based reformulation that enforces constraints through Lagrange terms instead of slack variables, drastically reducing quantum resource demands. An RL agent, trained with Soft Actor–Critic, adaptively tunes the Lagrange penalties to improve convergence and feasibility. Experiments show that RL-Q-ALM outperforms static-penalty and plain VQE baselines in both …

Food Recognition With Visual Language Models: Search Re-Ranking Or Retrieval-Augmented Generation?, Kian Yu Gan, Phuong Anh Nguyen, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Despite the rapid advances in Visual Language Models (VLMs), these models struggle to recognize culture-specific food items. While VLMs are effective in recognizing popular cultural dishes, their performance is suboptimal for dishes that are unique but not widely known internationally. Specifically, VLMs often generate either generic labels or hallucinated names for dishes that are localized to a particular culture. As a result, retrieval-augmented generation (RAG), which retrieves relevant recipes as references for VLMs, emerges as a promising approach. Nevertheless, recipe retrieval, which is itself imperfect, could mislead VLMs into generating inaccurate or culturally inappropriate dish names. This paper presents a …

Security-Enhanced Decentralized Conditional Privacy-Preserving Authentication In Vanets, Suqin Luo, Xinghua Li, Yinbin Miao, Xuelin Cao, Zhan Zhang, Yunwei Wang, Deng R.H.

Research Collection School Of Computing and Information Systems

To ensure the legitimacy of communicators while ad dressing the privacy concerns of vehicles in vehicular ad-hoc networks (VANETs), conditional privacy-preserving authentication (CPPA) schemes have been proposed. Given that existing schemes suffer from single point of failure due to centralized authorities, several distributed CPPA schemes have been proposed. However, these schemes all ignore the tight cementation between system secret keys and the authority, which could be a serious threat to system security, that the compromised authority may leak the system secret key. To address these issues, we propose a security enhanced decentralized conditional privacy-preserving authentication (DCPPA) scheme. DCPPA first introduces …

Cross-Modal Proxy Evolving For Ood Detection With Vision-Language Models, Hao Tang, Yu Liu, Shuanglin Yan, Fei Shen, Shengfeng He, Jing Qin

Research Collection School Of Computing and Information Systems

Reliable zero-shot detection of out-of-distribution (OOD) inputs is critical for deploying vision-language models in open-world settings. However, the lack of labeled negatives in zero-shot OOD detection necessitates proxy signals that remain effective under distribution shift. Existing negative-label methods rely on a fixed set of textual proxies, which (i) sparsely sample the semantic space beyond in-distribution (ID) classes and (ii) remain static while only visual features drift, leading to cross-modal misalignment and unstable predictions. In this paper, we propose CoEvo, a training- and annotation-free test-time framework that performs bidirectional, sample-conditioned adaptation of both textual and visual proxies. Specifically, CoEvo introduces a …

Tempo: Training-Time Equilibration Of Modalities For Per-Sample Optimization In Multimodal Sentiment, Yi Zhao, Erik Cambria, Xiaosong E, Xianxun Zhu

Research Collection School Of Computing and Information Systems

Multimodal sentiment models often become over-reliant on the “easiest” modality (typically text), leading to three coupled sub-problems: (i) representation-level dominance, where weaker modalities contribute little to the fused representation; (ii) optimization-level dominance, where the strongest modality drives most gradient updates and suppresses learning in others; and (iii) robustness degradation, where audio or vision fail under noise or missing inputs at test time. We present TEMPO, a plug-and-play training framework that mitigates these issues by rebalancing learning pressure across modalities while leaving inference unchanged. For each mini-batch, TEMPO estimates relative modality strength and applies two synchronized, training-only controls: selective forward attenuation …

Airaclex: Automated Detection Of Price Oracle Manipulations Via Llm-Driven Knowledge Mining And Prompt Generation, Bo Gao, Yuan Wang, Qingsong Wei, Yong Liu, Rick Siow Mong Goh, David Lo

Research Collection School Of Computing and Information Systems

Decentralized finance (DeFi) applications depend on accurate price oracles to ensure secure and fair transactions. However, poorly integrated oracles remain susceptible to manipulation, enabling attackers to exploit smart contract logic for unfair asset valuation and financial gain. While many such vulnerabilities are only detected after deployment, smart contracts are typically immutable once deployed, making post-hoc fixes costly or infeasible. This highlights the critical need for detecting oracle manipulation risks before deployment. In this paper, we propose AiRacleX, a novel LLM-driven framework that enables pre-deployment detection of price oracle manipulation vulnerabilities by leveraging the complementary strengths of multiple large language models …

Look, Compare And Draw: Differential Query Transformer For Automatic Oil Painting, Lingyu Liu, Yaxiong Wang, Li Zhu, Lizi Liao, Zhedong Zheng

Research Collection School Of Computing and Information Systems

This work introduces a new approach to automatic oil painting that emphasizes the creation of dynamic and expressive brushstrokes. A pivotal challenge lies in mitigating the duplicate and common-place strokes, which often lead to less aesthetic outcomes. Inspired by the human painting process, i.e., observing, comparing, and drawing, we incorporate differential image analysis into a neural oil painting model, allowing the model to effectively concentrate on the incremental impact of successive brushstrokes. To operationalize this concept, we propose the Differential Query Transformer (DQ-Transformer), a new architecture that leverages differentially derived image representations enriched with positional encoding to guide the stroke …

Portfoliopilot: An Agentic Platform For Financial Portfolio Management Algorithm Development And Evaluation, Jared Chan Xu Yang, Haokai Ma, Yunshan Ma

Research Collection School Of Computing and Information Systems

Developing new portfolio-management algorithms typically demands substantial programming effort, limiting rapid experimentation and excluding finance professionals without coding skills. Current robo-advisory tools offer pre-built but rigid strategies, restricting customization and experimentation. We introduce PortfolioPilot, an open-source, agentic platform that enables users to generate bespoke portfolio through natural-language descriptions. Leveraging the Anthropic Claude API, PortfolioPilot dynamically synthesizes executable TypeScript algorithms that run in the frontend with security validation. The system integrates real-time backtesting with historical market data, classical optimization algorithms (Markowitz, LSTM, ARIMA), and interactive performance visualizations.

Potent But Stealthy: Rethink Profile Pollution Against Sequential Recommendation Via Bi-Level Constrained Reinforcement Paradigm, Jiajie Su, Zihan Nan, Yunshan Ma, Xiaobo Xia, Xiaohua Feng, Weiming Liu, Xiang Chen, Xiaolin Zheng, Chaochao Chen

Research Collection School Of Computing and Information Systems

Sequential Recommenders, which exploit dynamic user intents through interaction sequences, are vulnerable to adversarial attacks. While existing attacks primarily rely on data poisoning, they require large-scale user access or fake profiles, thus lacking practicality. In this paper, we focus on the Profile Pollution Attack that subtly contaminates partial user interactions to induce targeted mispredictions. Previous PPA methods suffer from two limitations, i.e., i) overreliance on sequence horizon impact restricts fine-grained perturbations on item transitions, and ii) holistic modifications cause detectable distribution shifts. To address these challenges, we propose a constrained reinforcement driven attack CREAT that synergizes a bi-level optimization framework …

Nondeterministic Polynomial-Time Problem Challenge: An Ever-Scaling Reasoning Benchmark For Llms, Chang Yang, Ruiyu Wang, Junzhe Jiang, Qi Jiang, Qinggang Zhang, Yanchen Deng, Shuxin Li, Shuyue Hu, Bo Li, Florian T. Pokorny, Xiao Huang, Xinrun Wang

Research Collection School Of Computing and Information Systems

Reasoning is the fundamental capability of large language models (LLMs). Due to the rapid progress of LLMs, there are two main issues of current benchmarks: i) these benchmarks can be crushed in a short time (less than 1 year), and ii) these benchmarks may be easily hacked. To handle these issues, we propose the ever-scalingness for building the benchmarks which are scaling over complexity against crushing, instance against hacking and exploitation, oversight for easy verification, and coverage for real-world relevance. This paper presents Nondeterministic Polynomial-time Problem Challenge (NPPC), an ever-scaling reasoning benchmark for LLMs. Specifically, the NPPC has three main …

Evaluating Large Language Models For Line-Level Vulnerability Localization, Jian Zhang, Chong Wang, Anran Li, Weisong Sun, Cen Zhang, Wei Ma, Yang Liu

Research Collection School Of Computing and Information Systems

Recently, Automated Vulnerability Localization (AVL) has attracted growing attention, aiming to facilitate diagnosis by pinpointing the specific lines of code responsible for vulnerabilities. Large Language Models (LLMs) have shown potential in various domains, yet their effectiveness in line-level vulnerability localization remains underexplored. In this work, we present the first comprehensive empirical evaluation of LLMs for AVL. Our study examines 19 leading LLMs suitable for code analysis, including ChatGPT and multiple open-source models, spanning encoder-only, encoder-decoder, and decoder-only architectures, with model sizes from 60M to 70B parameters. We evaluate three paradigms including few-shot prompting, discriminative fine-tuning, and generative fine-tuning with and …

Interpretable Multimodal Zero Shot Ecg Diagnosis Via Structured Clinical Knowledge Alignment, Jialu Tang, Hung Manh Pham, Ignace De Lathauwer, Henk S. Schipper, Yuan Lu, Dong Ma, Aaqib Saeed

Research Collection School Of Computing and Information Systems

Electrocardiogram (ECG) interpretation is essential for cardiovascular disease diagnosis, but current automated systems often struggle with transparency and generalization to unseen conditions. To address this, we introduce ZETA, a zero-shot multimodal framework designed for interpretable ECG diagnosis aligned with clinical workflows. ZETA uniquely compares ECG signals against structured positive and negative clinical observations, which are curated through an LLM-assisted, expertvalidated process, thereby mimicking differential diagnosis. Our approach leverages a pre-trained multimodal model to align ECG and text embeddings without disease-specific fine-tuning. Empirical evaluations demonstrate ZETA’s competitive zero-shot classification performance and, importantly, provide qualitative and quantitative evidence of enhanced interpretability, grounding …

Awareness And Decision-Making In Cryptocurrency Investment Among Students In Guwahati: A Comprehensive Study, Rituparna Roy Dr, Anupam Chanda Dr, Bidangsha Basumatary

The Indonesian Capital Market Review

This study investigates the awareness and decision-making processes related to cryptocurrency investment among students in Guwahati, Assam. Cryptocurrency, a form of digital money designed for online transactions without government or bank oversight, has initiated significant shifts in the global financial sector. The decentralization of cryptocurrencies offers transparency, security, and efficiency, challenging traditional financial systems. Despite the growing global interest in cryptocurrencies, their adoption faces barriers such as limited technological expertise, regulatory uncertainty, and security concerns. These issues are particularly pronounced among students, a demographic increasingly interested in digital currencies but often lacking foundational financial knowledge. The research aims to fill …

Green Credit, Climate Risk, And Credit Risk In The Indonesian Banking Industry, Titi Dewi Warninda, Shelby Devianty Widodo

The Indonesian Capital Market Review

As the largest archipelagic country, Indonesia's industries and regions are particularly vulnerable to the impacts of climate change. This research examines the effects of green credit policy and climate risk, specifically sea level rise and precipitation, on bank credit risk. Using data from 2019 to 2023 and system GMM, the research results show that the higher the sea level rise and precipitation, the higher the credit risk. The findings of this research also indicate that a higher proportion of green credit lowers bank credit risk, and bank inefficiency strengthens the impact of green credit on credit risk. The results of …

Pedagogical Readiness And Adaptability In Higher Education In Egypt: An Exploration Of Generational Disparities In Ai Adoption., Maha Ahmed Zaki Dajani, Israa Lewaa, Hadia Fakhreldin

Business Administration

ABSTRACT

Dajani, M., LewaaElhamd, I., & FakhrEldin, H. (2025). Pedagogical readiness and adaptability in higher education in Egypt: An exploration of generational disparities in AI adoption. In Conference proceedings for the Annual Conference of Business, Economics and Politics in the Middle East (BEP-ME) 2025 (pp. 96,116). The British University in Egypt.

This study investigates generational differences in the adoption of AI tools in Egyptian higher education, examining how pedagogical readiness and adaptability influence engagement among students and educators. It addresses a key gap in the literature—the lack of an integrated pedagogical framework combining Kolb’s Experiential Learning Theory and Constructivist …

The Right To Seek Joy, Tyler Rose Clemons

Faculty Publications

Within the past three years, roughly half of American states have restricted access to gender-affirming medical treatment for children. In this article, I argue that these bans violate transgender children’s right to liberty guaranteed by the Fourteenth Amendment’s Due Process Clause. I do so by excavating the Framers’ understanding of liberty as the right to seek joy. Rooted in the philosophies of John Locke and Epicurus, the Framers understood liberty as the right to make important life decisions according to one’s subjective preferences without undue interference from the government. Based on this understanding, I develop a new framework for substantive …

Abuse Of Contract: A Proposal For A New Cause Of Action, Miriam A. Cherry

Faculty Publications

With the growth of online commerce and the platform economy, many companies are including provisions in their online terms and conditions that extend far beyond what reasonable consumers would expect. Some terms and conditions purport to bind customers to separate contracts in future transactions that have little to do with the first contract. Other boilerplate purports to cover family members of the customer who created an account. Some retailers have argued that people shopping in their brick-and-mortar stores are subject to terms and conditions because those shoppers had at some point previously created an online account. For example, Disney argued …

Usage Of Valved Conduit In Replacing The Mitral Valve In Heavily Calcific Or Destroyed Annulus: A Prospective Cohort Study, Yosry M Thakeb, Ahmed Kamel Abdel Ghany Hassan, Wael Abdelatief Mohamed Elhakeem

Journal of Medicine in Scientific Research

Background: Heavily calcified or destroyed mitral annulus present significant technical challenges for conventional valve replacement, often requiring alternative surgical strategies. Aim: To evaluate the safety, efficacy, operative outcomes, and the competency of valved conduit in patients with heavily calcified or destroyed mitral valve annulus. Methods: Fifteen patients (mean age 58.8±8.21 years, 53.3% female) underwent valved conduit mitral valve replacement at the Cardiothoracic Surgery Department, National Heart Institute, General Organization for Teaching Hospitals and Institutes (GOTHI), Egypt. Preoperatively, 80% presented in NYHA class III-IV with mean ejection fraction of 37.6±7.65% and pulmonary artery pressure of 50.6±11.39 mmHg. Bioprosthetic valves were used …

Global Perspectives On Esg And Sdgs In Aviation, Leila Halawi

Publications

ESG implementation in aviation and airline operations has progressed significantly in the past few years. ESG is thought of as a source of competitive advantage. This research investigates the complex connection between ESG practices, SDG alignment, and trust-building in airline operations. We examine how airlines navigate these complex dynamics by drawing on literature and case studies from three distinct regions: the United States, Europe, and South America. We synthesize existing knowledge to illuminate pathways toward a more sustainable and trusted aviation industry and offer insights into successful approaches, persistent challenges, and emerging trends. © 2026 selection and editorial matter, Joanna …

Front Matter, Arianna Medina

Western Journal of Orthopaedics

No abstract provided.

21st Century Perspective On The Changing Pattern Of Nerve Injuries From Gunshot Wounds In The U.S., Thomas A. Decoster

Western Journal of Orthopaedics

Gunshot wounds (GSWs) with nerve injuries in the 21st century differ significantly from those reported in the 20th century. The vast majority are now low-velocity civilian injuries, in contrast to high-velocity military injuries previously reported. The rate of nerve injury in civilian GSWs is approximately 5%, compared with the 30% reported in military cohorts. However, the most common pattern of nerve injury in the current civilian population is neurotmesis and partial neurotmesis, in contrast to the majority axonotmesis of the military cohorts. In the 20th century, treatment generally consisted of watchful waiting for signs of spontaneous recovery over three months …

Peripheral Nerve Repair And Reconstruction: Current Techniques, Adjuncts, And Emerging Therapies, Niklaus Skipp, Lana Dokic, Christina Wassef, Jazzlyn Gonzalez, Ana Love, Heather Mercer, Deana Mercer

Western Journal of Orthopaedics

Peripheral nerve injuries require reconstruction when direct, tension-free repair is not possible. A range of reconstructive strategies are used to restore continuity and promote axonal regeneration, including graft-based reconstruction, nerve transfers, conduit-based repair, supercharged end-to-side augmentation, and emerging regenerative therapies. Autologous interfascicular nerve grafts and vascularized grafts remain established techniques, whereas processed nerve allografts provide a donor-sparing alternative. Nerve transfers are increasingly used for proximal injuries with long regeneration distances, and conduits are an option for gaps shorter than 5 mm. Nerve-wrapping techniques are used to reduce perineural scarring and preserve gliding in complex or revision cases. Emerging adjunctive therapies, …

Increased Mortality And Reduced Survival In Nonagenarians With Hip Fractures: Implications For Geriatric Care, Roman Austin, Julio Avila, Audrey Wassef, Kate Parker, Katherine Gavin

Western Journal of Orthopaedics

Background: Hip fractures in nonagenarians (patients aged ≥ 90 years) are becoming increasingly common as the population ages, yet outcomes in this group remain poorly characterized. This study compared in-hospital mortality and survivorship at three months, six months, and one year after hip fracture surgery in nonagenarians with a younger elderly cohort aged 65 years to 89 years. Secondary outcomes included fracture characteristics, surgical management, and discharge disposition. Methods: A retrospective chart review was conducted on patients who underwent hip fracture surgery at a single Level I Trauma Center from August 2019 to December 2021. Patients were grouped into nonagenarians …

Exploring The Interaction Between Cranial Nerves V And Vii In Chronic Eyelid Myokymia: A Case Report, Karina Miramontes, Adam Walsh, Tomas Tafoya

Western Journal of Orthopaedics

Eyelid myokymia involves involuntary contractions of the orbicularis oculi muscle and is commonly associated with stress, fatigue, and craniocervical factors. Emerging evidence suggests that altered trigeminocervical interactions and craniomandibular muscle tension may contribute to symptom persistence; however, the condition remains underrecognized in physical therapy. This report describes a 65-year-old woman with chronic benign eyelid myokymia and cervical pain who completed 12 physical therapy sessions that included suboccipital functional dry needling, temporomandibular soft-tissue mobilization (STM), and cervical stabilization exercises. A reduction in eyelid myokymia was first observed at the fifth visit, coinciding with the initiation of temporomandibular STM. These findings suggest …

Median Nerve Intraneural Hematoma As An Intraoperative Finding During Carpal Tunnel Release: A Case Report, Ana Silva, Gil Gonrtre, Nikalus Skipp, Ana Love, Deana Mercer

Western Journal of Orthopaedics

Carpal tunnel syndrome (CTS) is the most common compressive neuropathy and typically progresses slowly. Intraoperatively, flexor tenosynovitis, nerve edema, or hourglass deformity may be observed. In rare cases, acute compression symptoms occur due to mass effect on the nerve. Intraneural hematoma of the median nerve is uncommon and has been reported primarily in acute CTS cases associated with trauma. This report describes an 87-year-old patient with a history of mild CTS who underwent carpal tunnel release due to worsening symptoms. After the initial incision, a thickened flexor retinaculum, an hourglass deformity of the median nerve, and an intraneural hematoma were …

Proximal Iliotibial Band Rupture In A 74-Year-Old High-Level, Female Athlete: A Case Report, Jeremiah M. Langsfeld, Joseph Esquibel, Dustin L. Richter

Western Journal of Orthopaedics

A 74-year-old female endurance athlete presented with progressive pain over the left proximal and lateral hip distal to the iliac crest. Symptoms developed over three weeks, impairing weightbearing. Magnetic resonance imaging demonstrated a high-grade tear of the proximal iliotibial band at its iliac crest insertion. The patient was treated nonoperatively and returned to high-level, asymptomatic competition three months after symptom onset. This case offers a nonoperative approach to the rare presentation of a proximal iliotibial band rupture.

Arthroscopic Treatment Of Extensive Synovial Chondromatosis Of The Knee: A Case Report, Gaurav Singh, Bhavna Singh, Rebecca Peebles, Justin Bartley

Western Journal of Orthopaedics

Synovial chondromatosis (SC) is a rare, benign monoarticular disorder characterized by intra-articular cartilaginous loose bodies resulting from synovial metaplasia, most commonly affecting the knee. The authors present the case of a 44-year-old man with progressive, debilitating left knee pain, mechanical symptoms, and functional limitations unresponsive to conservative treatment. Radiographs were unremarkable, but magnetic resonance imaging (MRI) demonstrated multifocal noncalcified intra-articular bodies consistent with SC. The patient underwent arthroscopic debridement of the knee with limited synovectomy. Intraoperative findings included innumerable intra-articular cartilaginous loose bodies throughout the knee, synovial proliferation, and grade II chondromalacia. At three months postoperatively, the patient had regained …

Arthroscopic Management Of A Loose Body In The Pisotriquetral Joint: A Case Report, Giovanni Chioda, Tomas Holy, Nicholas Newcomb, Nathan Morrell

Western Journal of Orthopaedics

The pisotriquetral joint is the smallest of the four joints comprising the wrist and is a source of ulnar-sided wrist pain. This condyloid joint connects the pisiform to the triquetrum and is supported by several surrounding ligaments. A variety of pathologies may affect the pisotriquetral joint, including the presence of loose bodies. Because of its small size and the inherent difficulty of visualization, the pisotriquetral joint is often overlooked as an independent joint. Techniques for arthroscopic visualization and loose-body removal have previously been described using the 6R and 4-5 portals. In the following case report, the authors describe successful visualization …

Play-Based Learning In Private International Preschools In Cairo: Teachers' Perspectives, Kesha L. Stovall

Theses and Dissertations

This thesis explores how play-based learning is practiced and contextualized in private, international preschools in Cairo, Egypt through the perspective of teachers. It calls upon both historical and contemporary theories of play and play pedagogies ranging from the times of Plato and Al-Farabi to the 21st century with Montessori and Dewey. Using a contemporary theory of play presented by Stuart Lester and Wendy Russell as a guiding framework, it examines how play and play-based learning are implemented, shaped and even challenged in a Cairene context. These contexts include sociocultural factors such as parents’ expectations and aspirations, institutional barriers, teacher development …