Scenario-Driven And Context-Aware Automated Accessibility Testing For Android Apps,
2025
Singapore Management University
Scenario-Driven And Context-Aware Automated Accessibility Testing For Android Apps, Yuxin Zhang, Sen Chen, Xiaofei Xie, Zibo Liu, Lingling Fan
Research Collection School Of Computing and Information Systems
Mobile accessibility is increasingly important nowadays as it enables people with disabilities to use mobile applications to perform daily tasks. Ensuring mobile accessibility not only benefits those with disabilities but also enhances the user experience for all users, making applications more intuitive and user-friendly. Although numerous tools are available for testing and detecting accessibility issues in Android applications, a large number of false negatives and false positives persist due to limitations in the existing approaches, i.e., low coverage of UI scenarios and lack of consideration of runtime context. To address these problems, in this paper, we propose a scenario-driven exploration …
Hello Again! Llm-Powered Personalized Agent For Long-Term Dialogue,
2025
Singapore Management University
Hello Again! Llm-Powered Personalized Agent For Long-Term Dialogue, Hao Li, Chenghao Yang, An Zhang, Yang Deng, Xiang Wang, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
Open-domain dialogue systems have seen remarkable advancements with the development of large language models (LLMs). Nonetheless, most existing dialogue systems predominantly focus on brief single-session interactions, neglecting the real-world demands for long-term companionship and personalized interactions with chatbots. Crucial to addressing this real-world need are event summary and persona management, which enable reasoning for appropriate long-term dialogue responses. Recent progress in the human-like cognitive and reasoning capabilities of LLMs suggests that LLM-based agents could significantly enhance automated perception, decision-making, and problem-solving. In response to this potential, we introduce a model-agnostic framework, the Long-term Dialogue Agent (LD-Agent), which incorporates three independently …
Flexfl: Flexible And Effective Fault Localization With Open-Source Large Language Models,
2025
Singapore Management University
Flexfl: Flexible And Effective Fault Localization With Open-Source Large Language Models, Chuyang Xu, Zhongxin Liu, Xiaoxue Ren, Gehao Zhang, Ming Liang, David Lo
Research Collection School Of Computing and Information Systems
Fault localization (FL) targets identifying bug locations within a software system, which can enhance debugging efficiency and improve software quality. Due to the impressive code comprehension ability of Large Language Models (LLMs), a few studies have proposed to leverage LLMs to locate bugs, i.e., LLM-based FL, and demonstrated promising performance. However, first, these methods are limited in flexibility. They rely on bug-triggering test cases to perform FL and cannot make use of other available bug-related information, e.g., bug reports. Second, they are built upon proprietary LLMs, which are, although powerful, confronted with risks in data privacy. To address these limitations, …
The Role Of Individual Values In Bryant University's Sustainability Efforts,
2025
Bryant University
The Role Of Individual Values In Bryant University's Sustainability Efforts, John Boccuzzi Iii
Honors Projects in Data Science
This research examines student, faculty, and staff perspectives on sustainability at Bryant University, with the goal of understanding how individual values align with the university's environmental initiatives. The objective is to assess perceptions of Bryant's current sustainability practices, explore how effectively these efforts are communicated across campus, and identify potential gaps between institutional action and community awareness. To achieve this, the study gathers qualitative data through an open-ended survey and applies sentiment analysis to interpret student attitudes toward sustainability. By analyzing these responses alongside Bryant's sustainability marketing efforts, this research will identify gaps between student engagement and institutional messaging The …
Breaking Down Terminology Of Clojure Error Messages For Beginner Programmers,
2025
University of Minnesota - Morris
Breaking Down Terminology Of Clojure Error Messages For Beginner Programmers, John Walbran, Jaydon Stanislowski, Tristan Kalvoda
Undergraduate Research Symposium 2025
The Clojure programming language has educational potential for beginner programmers due to its clean, simple syntax and its strong focus on functional programming, an important aspect of CSci education. However, one weakness of Clojure lies in its error messages, which are messages that programmers receive when a program goes wrong. The terminology and shorthands used to convey necessary information for understanding the error are often confusing to novices. The issue is exacerbated by the fact that the error messages are phrased in terms of the underlying programming language – Java – which beginner programmers may typically be unfamiliar with. A …
From Adversarial Attacks To Robust Classifiers - A Study In Social Media Spam Detection - Black Box & White Box,
2025
Bellarmine University
From Adversarial Attacks To Robust Classifiers - A Study In Social Media Spam Detection - Black Box & White Box, Jonathan Jose Penaloza Rumie
Undergraduate Theses
Adversarial attacks pose a significant threat to the reliability of machine learning-based spam detection systems in social media. This undergraduate thesis, "From Adversarial Attacks to Robust Classifiers: A Study in Social Media Spam Detection – Black Box & White Box," systematically examines the impact of both black-box and white-box adversarial attacks on a range of spam classifiers, including Logistic Regression, Decision Trees, Random Forests, K-Nearest Neighbors, Bagging, Gradient Boosting, and Support Vector Machines. Leveraging a novel dataset derived from Twitter spam messages and enhanced with adversarial perturbations such as synonym replacement and character-level modifications, this study evaluates classifier performance under …
Coding An Assignment Calculator Exclusively With Chatgpt,
2025
Fort Hays State University
Coding An Assignment Calculator Exclusively With Chatgpt, Andy Tincknell, Heather P. Vandyne, Lisa K. Bell
SACAD: Scholarly Activities
Large Language Models like ChatGPT are influencing higher education and society in broader ways, including the coding and programming of applications and websites (Silva et al., 2024). This poster will profile how Forsyth Library, with no coders on staff, used ChatGPT to program an Assignment Calculator LibGuide without human coding. It details the process, challenges, and outcomes while highlighting AI’s potential to enhance resources for academic success and considers its efficacy and ethical implications.
Binge Buddies,
2025
St. Mary's University
Binge Buddies, Joshua Uribe
Posters - 2025
Many people struggle to keep track of the shows and movies they’ve watched or plan to watch. Existing streaming platforms often provide limited or cluttered tracking features, making it challenging to stay organized. Binge Buddies addresses this issue by centralizing watchlists and viewing history in one streamlined location. The website is designed to simplify the binge-watching experience, helping users stay on top of their content and discover new shows/movies. Which makes the experience a smoother and more enjoyable experience.
Cyber Safe,
2025
St. Mary's University
Cyber Safe, Hiram Franco, Laurene Robinson, Joshua Do, Enrique Martinez, Han Vu
Posters - 2025
With the rapid rise of cyber threats, understanding malware behavior is more crucial than ever. Millions of new malware variants emerge annually, compromising personal data, financial information, and entire networks. While no system is entirely immune, cybersecurity education can help mitigate risks. CYBERSAFE is a sandbox malware analyzer designed to enhance malware detection and analysis skills. By running malware samples in a controlled virtual environment, users can observe real-time file modifications, network activity, and system changes. The tool also includes interactive exercises and quizzes to reinforce learning. CYBERSAFE bridges the gap between theory and practice, providing hands-on experience to help …
Frame-Voyager: Learning To Query Frames For Video Large Language Models,
2025
Singapore Management University
Frame-Voyager: Learning To Query Frames For Video Large Language Models, Sicheng Yu, Chengkai Jin, Huanyu Wang, Zhenghao Chen, Sheng Jin, Zhongrong Zuo, Xiaolei Xu, Zhenbang Sun, Bingni Zhang, Jiawei Wu, Hao Zhang, Qianru Sun
Research Collection School Of Computing and Information Systems
Video Large Language Models (Video-LLMs) have made remarkable progress in video understanding tasks. However, they are constrained by the maximum length of input tokens, making it impractical to input entire videos. Existing frame selection approaches, such as uniform frame sampling and text-frame retrieval, fail to account for the information density variations in the videos or the complex instructions in the tasks, leading to sub-optimal performance. In this paper, we propose Frame-Voyager that learns to query informative frame combinations, based on the given textual queries in the task. To train Frame-Voyager, we introduce a new data collection and labeling pipeline, by …
Chatcrs: Incorporating External Knowledge And Goal Guidance For Llm-Based Conversational Recommender Systems,
2025
Singapore Management University
Chatcrs: Incorporating External Knowledge And Goal Guidance For Llm-Based Conversational Recommender Systems, Chuang Li, Yang Deng, Hengchang Hu, Min-Yen Kan, Haizhou Li
Research Collection School Of Computing and Information Systems
This paper aims to efficiently enable large language models (LLMs) to use external knowledge and goal guidance in conversational recommender system (CRS) tasks. Advanced LLMs (e.g., ChatGPT) are limited in domain-specific CRS tasks for 1) generating grounded responses with recommendation-oriented knowledge, or 2) proactively leading the conversations through different dialogue goals. In this work, we first analyze those limitations through a comprehensive evaluation, showing the necessity of external knowledge and goal guidance which contribute significantly to the recommendation accuracy and language quality. In light of this finding, we propose a novel ChatCRS framework to decompose the complex CRS task into …
Alphaedit: Null-Space Constrained Knowledge Editing For Language Models,
2025
Singapore Management University
Alphaedit: Null-Space Constrained Knowledge Editing For Language Models, Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Jie Shi, Xiang Wang, Xiangnan He, Tat‑Seng Chua
Research Collection School Of Computing and Information Systems
Large language models (LLMs) often exhibit hallucinations, producing incorrector outdated knowledge. Hence, model editing methods have emerged to enabletargeted knowledge updates. To achieve this, a prevailing paradigm is the locatingthen-editing approach, which first locates influential parameters and then edits themby introducing a perturbation. While effective, current studies have demonstrated that this perturbation inevitably disrupt the originally preserved knowledge within LLMs, especially in sequential editing scenarios. To address this, we introduce AlphaEdit, a novel solution that projects perturbation onto the null space of the preserved knowledge before applying it to the parameters. We theoretically prove that this projection ensures the output …
A Functional Software Reference Architecture For Llm-Integrated Systems,
2025
Singapore Management University
A Functional Software Reference Architecture For Llm-Integrated Systems, Alessio Bucaioni, Martin Weyssow, Junda He, Yunbo Lyu, David Lo
Research Collection School Of Computing and Information Systems
The integration of large language models into software systems is transforming capabilities such as natural language understanding, decision-making, and autonomous task execution. However, the absence of a commonly accepted software reference architecture hinders systematic reasoning about their design and quality attributes. This gap makes it challenging to address critical concerns like privacy, security, modularity, and interoperability, which are increasingly important as these systems grow in complexity and societal impact. In this paper, we describe our emerging results for a preliminary functional reference architecture as a conceptual framework to address these challenges and guide the design, evaluation, and evolution of large …
Enhancing Llm-Based Coding Tools Through Native Integration Of Ide-Derived Static Context,
2025
Singapore Management University
Enhancing Llm-Based Coding Tools Through Native Integration Of Ide-Derived Static Context, Yichen Li, Yun Peng, Yintong Huo, R. Michael Lyu
Research Collection School Of Computing and Information Systems
Large Language Models (LLMs) have achieved remarkable success in code completion, as evidenced by their essential roles in developing code assistant services such as Copilot. Being trained on in-file contexts, current LLMs are quite effective in completing code for single source files. However, it is challenging for them to conduct repository-level code completion for large software projects that require cross-file information. Existing research on LLM-based repository-level code completion identifies and integrates cross-file contexts, but it suffers from low accuracy and limited context length of LLMs. In this paper, we argue that Integrated Development Environments (IDEs) can provide direct, accurate and …
Bootstrapping Language Models With Dpo Implicit Rewards,
2025
Singapore Management University
Bootstrapping Language Models With Dpo Implicit Rewards, Changyu Chen, Zichen Liu, Chao Du, Tianyu Pang, Qian Liu, Arunesh Sinha, Pradeep Varakantham, Min Lin
Research Collection School Of Computing and Information Systems
Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the process from past work in reinforcement learning from human feedback (RLHF) by bypassing the reward learning stage in RLHF. DPO, after training, provides an implicit reward model. In this work, we make a novel observation that this implicit reward model can by itself be used in a bootstrapping fashion to further align the LLM. Our approach is to use the rewards from a current LLM model to construct a preference dataset, which is then used …
Addressing Equity Issues In Elementary Computer Science Education: Knowns, Unknowns, And Implications For Future Work,
2025
California State University, Dominguez Hills
Addressing Equity Issues In Elementary Computer Science Education: Knowns, Unknowns, And Implications For Future Work, Mike Karlin, Yin-Chan Janet Liao, Swati Mehta, Afreen Iqbal, Mahya Minaiy, Minhye Son, Jessica Pandya
Journal of Computer Science Integration
In 2016, a national coalition of stakeholders released the K-12 computer science (CS) framework. In the time since, there has been an increased push at the local, state, and national level to integrate CS knowledge and skills into K-12 education. Despite this push, significant equity issues exist within the field. While growing research has been done on CS equity issues at the high school level, we know these equity gaps often begin to emerge in elementary school where less is known. Therefore, we conducted a systematic literature review to better understand and explore the elementary CS equity research landscape from …
Birdie: Natural Language-Driven Table Discovery Using Differentiable Search Index,
2025
Singapore Management University
Birdie: Natural Language-Driven Table Discovery Using Differentiable Search Index, Yuxiang Guo, Zhonghao Hu, Yuren Mao, Baihua Zheng, Yunjun Gao, Mingwei Zhou
Research Collection School Of Computing and Information Systems
Natural language (NL)-driven table discovery identifies relevant tables from large table repositories based on NL queries. While current deep-learning-based methods using the traditional dense vector search pipeline, i.e., representation-index-search, achieve remarkable accuracy, they face several limitations that impede further performance improvements: (i) the errors accumulated during the table representation and indexing phases affect the subsequent search accuracy; and (ii) insufficient query-table interaction hinders effective semantic alignment, impeding accuracy improvements. In this paper, we propose a novel framework Birdie, using a differentiate search index. It unifies the indexing and search into a single encoder-decoder language model, thus getting rid of error …
Attackg+: Boosting Attack Graph Construction With Large Language Models,
2025
Singapore Management University
Attackg+: Boosting Attack Graph Construction With Large Language Models, Yongheng Zhang, Tingwen Du, Yunshan Ma, Xiang Wang, Yi Xie, Guozheng Yang, Yuliang Lu, Ee‑Chien Chang
Research Collection School Of Computing and Information Systems
Attack graph construction seeks to convert textual cyber threat intelligence (CTI) reports into structuredrepresentations, portraying the evolutionary traces of cyber attacks. Even though previous research hasproposed various methods to construct attack graphs, they generally suffer from limited generalizationcapability to diverse knowledge types as well as requirement of expertise in model design and tuning.Addressing these limitations, we seek to utilize Large Language Models (LLMs), which have achieved enormoussuccess in a broad range of tasks given exceptional capabilities in both language understanding and zeroshot task fulfillment. Thus, we propose a fully automatic LLM-based framework to construct attack graphsnamed: AttacKG+. Our framework consists …
Adversarial Attacks And Defense Methods In Robotic Systems,
2025
University of South Alabama
Adversarial Attacks And Defense Methods In Robotic Systems, Thanh D. Le
Shelby Hall Graduate Research Forum Presentations
Presentation slides for a presentation given at the 1st annual Shelby Hall Graduate Research Forum at the University of South Alabama.
Choosing Robust Leadership: Encompassing The Best-Of-N Model And Swarm Intelligence Optimization For Heterogeneous Multiple Autonomous Unmanned Aerial Vehicle Systems,
2025
University of South Alabama
Choosing Robust Leadership: Encompassing The Best-Of-N Model And Swarm Intelligence Optimization For Heterogeneous Multiple Autonomous Unmanned Aerial Vehicle Systems, Kudamuhandiramlage Harith Kolitha Warnakulasooriya
Shelby Hall Graduate Research Forum Presentations
Presentation slides for a presentation given at the 1st annual Shelby Hall Graduate Research Forum at the University of South Alabama.
