Computer Sciences Commons^™

Identifying And Mitigating Api Misuse In Large Language Models, Terry Yue Zhuo, Junda He, Jiamou Sun, Zhenchang Xing, David Lo, John Grundy, Xiaoning Du

Research Collection School Of Computing and Information Systems

API misuse in code generated by large language models (LLMs) presents a serious and growing challenge in software development. While LLMs demonstrate impressive code generation capabilities, their interactions with complex library APIs are often error-prone, potentially leading to software failures and vulnerabilities. In this paper, we conduct a large-scale study of API misuse patterns in LLM-generated code, analyzing both method selection and parameter usage across Python and Java, using three representative LLMs (StarCoder-7B, Qwen2.5-Coder-7B, and GitHub Copilot). Based on extensive manual annotation of 3,209 method-level and 3,492 parameter-level misuses, we identify and categorize four recurring misuse types by building on …

Invert Your Prompt: Editing-Aware Diffusion Inversion, Yangyang Xu, Wenqi Shao, Yong Du, Haiming Zhu, Yang Zhou, Jiayuan Xie, Ping Luo, Shengfeng He

Research Collection School Of Computing and Information Systems

Recent advancements in text-guided diffusion models have enabled powerful image manipulation capabilities. However, balancing reconstruction fidelity and editability for real images remains a significant challenge. In this work, we introduce Editing Inversion (EditInv), a novel framework that inverts and edits real images for specific editing tasks by optimizing specific prompt embeddings within the extended  space. By leveraging distinct embeddings across different U-Net layers and time steps, EditInv seamlessly integrates inversion and editing through reciprocal optimization, ensuring both high fidelity and precise editability. This hierarchical editing mechanism classifies tasks into structure, appearance, and global edits, optimizing only those embeddings that are …

Optimizing And Fortifying Ai Software Through The Lens Of Artifact Synthesis, Jieke Shi

Dissertations and Theses Collection (Open Access)

Artificial Intelligence (AI) has transformed the software landscape, ushering in a new era of intelligent systems that increasingly shape our daily lives. This transformation is evident in various domains, including Software Engineering (SE), where Large Language Models (LLMs) support many development tools, and control systems, where self-driving cars and autonomous drones rely on deep learning models for real-time decision-making. These AI systems are collectively referred to as AI software, with the former categorized as AI4SE software (AI for Software Engineering) and the latter as AI4Control software (AI for Control). As AI software becomes central to modern computing infrastructure, its reliability …

How Agile Became The Design Philosophy Of Ai Fishbowl Under Real-World Constraints, Jad Saad

University Honors Theses

This capstone review examines the development of AI Fishbowl, a public-facing, interactive artificial intelligence system, as a case study in how Agile methods evolve from a project management tool into a design philosophy under real-world constraints. Although the project adopted an Agile workflow early on through a Kanban-style task management approach, the initial system design and architecture were still shaped by a largely plan-first mindset. This created a mismatch between flexible process and rigid design assumptions, which became increasingly apparent as the team moved from high-level architecture into implementation.

A critical turning point occurred when early architectural plans proved difficult …

Codeultrafeedback: An Llm-As-A-Judge Dataset For Aligning Large Language Models To Coding Preferences, Martin Weyssow, Aton Kamanda, Xin Zhou, Houari Sahraoui

Research Collection School Of Computing and Information Systems

Evaluating the alignment of large language models (LLMs) with user-defined coding preferences is a challenging endeavor that requires a deep assessment of LLMs' outputs. Existing methods and benchmarks rely primarily on automated metrics and static analysis tools, which often fail to capture the nuances of user instructions and LLM outputs. To address this gap, we introduce the LLM-as-a-Judge evaluation framework and present CodeUltraFeedback, a comprehensive dataset for assessing and improving LLM alignment with coding preferences. CodeUltraFeedback consists of 10,000 coding instructions, each annotated with four responses generated from a diverse pool of 14 LLMs. These responses are annotated using GPT-3.5 …

Designing For Trust In Chat-Based Question Answering Systems: An Exchange-Based Retrieval Approach, Nathan Mccutchen

Master's Theses

Community chat platforms such as Discord and Slack support spontaneous, collaborative communication but make it difficult to retrieve previously discussed information. As conversations accumulate, valuable exchanges become buried, leading to repeated questions and sustained burden on experienced community members.

This work contributes a set of design requirements for question-answering systems operating over unstructured chat data, a Discord bot prototype implementing those requirements named Echo, and an empirical evaluation of how such a system affects user trust. Rather than encoding discrete question-answer pairs or generating synthetic responses with a language model, Echo indexes conversation topics for semantic retrieval and presents results …

Emulating Camera Parameters For A Digital Twin Lunar Terrain Simulation, Samuil Nikolov

Student Research Symposium (SRS)

Digital twin simulations play an integral role in the design, validation and implementation of a plethora of systems in any industry - including aerospace. EagleCam 2 presents a great technical challenge, where we need to evaluate how our systems will do data acquisition best - image capturing in particular. In order to assist with the design and validation of our systems, a digital twin that emulates the Lunar environment as we expect it to be during the lifecycle of the mission is a crucial component. Such digital twin system allows us to simulate all the parameters that are considered variable …

Fortifying The Seams Between C/C++ And Rust: Characterizing Bugs In Interop Tools, Xuemeng Cai, Jiakun Liu, Cunyang Liu, Lingfeng Bao, Yijun Yu, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Rust has become increasingly popular in recent years due to its safety and high performance. Despite these advantages, Rust projects rarely start from scratch in practice, and many Rust-based systems instead use hybrid programming, where Rust interoperates with existing C/C++ code. To reduce the manual effort involved in this interoperation (interop) process, several interop tools have been proposed to facilitate hybrid programming between Rust and C/C++. However, the challenges and limitations of these tools remain largely unexplored, leaving developers unclear about the future directions and users unclear about the appropriate usage scenarios. To fill the gap, we mined 320 bugs …

The Feelit System: Application Content-Aware Perspectives And Challenges On Understanding User Likes In Social Network Posts, Konstantinos Theocharidis, Hady W. Lauw, Panagiotis Karras

Research Collection School Of Computing and Information Systems

In a series of our prior works, we study influence and subscription maximization problems in social networks that are based on posts having influential content; as content we consider a set of features where each feature corresponds to a specific social network page, whereas influence and subscription relate to gaining the postlike and subscription-to-brand page of targeted users, respectively; subscription is conceptually achieved as repetitive influence on users. So, both influence and subscription depend on content that gains the likes of users; however, to be realistic, modeling and estimating such likes is a complex problem that has not been adequately …

Zero-Shot Video Translation Via Token Warping, Haiming Zhu, Yangyang Xu, Jun Yu, Shengfeng He

Research Collection School Of Computing and Information Systems

With the revolution of generative AI, video-related tasks have been widely studied. However, current state-of-the-art video models still lag behind image models in visual quality and user control over generated content. In this paper, we introduce TokenWarping, a novel framework for temporally coherent video translation. Existing diffusion-based video editing approaches rely solely on key and value patches in self-attention to ensure temporal consistency, often sacrificing the preservation of local and structural regions. Critically, these methods overlook the significance of the query patches in achieving accurate feature aggregation and temporal coherence. In contrast, TokenWarping leverages complementary token priors by constructing temporal …

Less Is More: Docstring Compression In Code Generation, Guang Yang, Yu Zhou, Wei Cheng, Xiangyu Zhang, Xiang Chen, Terry Yue Zhuo, Xin Zhou, Ke Liu, David Lo, Taolue Chen

Research Collection School Of Computing and Information Systems

The widespread use of Large Language Models (LLMs) in software engineering has intensified the need for improved model and resource efficiency. In particular, for neural code generation, LLMs are used to translate function/method signature and DocString to executable code. DocStrings, which capture user requirements for the code and are typically used as the prompt for LLMs, often contain redundant information. Recent advancements in prompt compression have shown promising results in Natural Language Processing (NLP), but their applicability to code generation remains uncertain. Our empirical study shows that the state-ofthe-art prompt compression methods achieve only about 10% reduction, as further reductions …

Vercation: Precise Vulnerable Open-Source Software Version Identification Based On Static Analysis And Llm, Yiran Cheng, Ting Zhang, Lwin Khin Shar, Shouguo Yang, Chaopeng Dong, David Lo, Shichao Lv, Zhiqiang Shi, Limin Sun

Research Collection School Of Computing and Information Systems

Open-source software (OSS) has experienced a surge in popularity, attributed to its collaborative development model and cost-effective nature. However, the adoption of specific software versions in development projects may introduce security risks when these versions bring along vulnerabilities. Current methods of identifying vulnerable versions typically analyze and extract the code features involved in vulnerability patches using static analysis with pre-defined rules. They then use code clone detection to identify the vulnerable versions. These methods are hindered by imprecision due to (1) the exclusion of vulnerability- irrelevant code in the analysis and (2) the inadequacy of code clone detection. This paper …

Exploring Jvm Garbage Collector Testing With Event-Coverage, Kai Zheng, Yingquan Zhao, Junjie Chen, Hanmo You, Haoyu Wang, Haoyu Wang, Tianchang Gao

Research Collection School Of Computing and Information Systems

Garbage Collection (GC) in the Java Virtual Machine (JVM) serves as an automatic memory management mechanism, efficiently reclaiming unused memory space in different production scenarios. To optimize JVM performance, developers typically fine-tune the garbage collector by identifying an optimal set of GC configurations for specific scenarios. Despite the sophisticated design of garbage collectors, they still have the potential for bugs in different settings, and these bugs can result in more severe consequences. Hence, comprehensive testing of these garbage collectors is imperative before their release. Code coverage criteria are typically employed to assess the comprehensiveness of a test suite. However, traditional …

Defending Code Language Models Against Backdoor Attacks With Deceptive Cross-Entropy Loss, Guang Yang, Yu Zhou, Xiangyu Zhang, Xiang Chen, Terry Yue Zhuo, David Lo, Taolue Chen

Research Collection School Of Computing and Information Systems

Code Language Models (CLMs), particularly those leveraging deep learning, have achieved significant success in code intelligence domain. However, the issue of security, particularly backdoor attacks, is often overlooked in this process. The previous research has focused on designing backdoor attacks for CLMs, but effective defenses have not been adequately addressed. In particular, existing defense methods from natural language processing, when directly applied to CLMs, are not effective enough and lack generality, working well in some models and scenarios but failing in others, thus fall short in consistently mitigating backdoor attacks. To bridge this gap, we first confirm the phenomenon of …

Fcghunter: Towards Evaluating Robustness Of Graph-Based Android Malware Detection, Shiwen Song, Xiaofei Xie, Ruitao Feng, Qi Guo, Sen Chen

Research Collection School Of Computing and Information Systems

Graph-based detection methods leveraging Function Call Graph (FCG) have shown promise for Android malware detection (AMD) due to their semantic insights. However, the deployment of malware detectors in dynamic and hostile environments raises significant concerns about their robustness. While recent approaches evaluate the robustness of FCG-based detectors using adversarial attacks, their effectiveness is constrained by the vast perturbation space, particularly across diverse models and features. To address these challenges, we introduce FCGHunter, a novel robustness testing framework for FCG-based AMD systems. Specifically, FCGHunter employs innovative techniques to enhance exploration and exploitation within this huge search space. Initially, it identifies critical …

Efficient Function Orchestration For Large Language Models, Xiaoxia Liu, Peng Di, Cong Li, Jun Sun, Jingyi Wang

Research Collection School Of Computing and Information Systems

Function calling is a fundamental capability of today's large language models, but sequential function calling posed efficiency problems. Recent studies have proposed to request function calls with parallelism support in order to alleviate this issue. However, they either delegate the concurrent function calls to users for execution which are conversely executed sequentially, or overlook the relations among various function calls, rending limited efficiency. This paper introduces LLMOrch, an advanced framework for automated, parallel function calling in large language models. The key principle behind LLMOrch is to identify an available processor to execute a function call while preventing any single processor …

A Virtual-Reality-Based Dental Simulator For Endodontics With Automated Formative Feedback, Yousef Salah Abo El Ela

Theses and Dissertations

Advancements in virtual reality (VR) and haptic technology are transforming the landscape of medical and dental education, offering new avenues for safe, immersive, and repeatable training experiences. Within dentistry, endodontics presents unique challenges for preclinical education due to anatomical complexity, limited access to extracted teeth, ethical concerns, and the shortcomings of conventional plastic models. Despite endodontics specific plastic teeth being available, they fall short of replicating the hardness of real extracted teeth, are relatively costly compared to generic plastic teeth, and are ultimately a disposable item which makes them inadequate as a sustainable long-term solution. Extracted teeth do a much …

Generalized Visual Relation Detection With Diffusion Models, Kaifeng Gao, Siqi Chen, Hanwang Zhang, Jun Xiao, Yueting Zhuang, Qianru Sun

Research Collection School Of Computing and Information Systems

Visual relation detection (VRD) aims to identify relationships (or interactions) between object pairs in an image. Although recent VRD models have achieved impressive performance, they are all restricted to pre-defined relation categories, while failing to consider the semantic ambiguity characteristic of visual relations. Unlike objects, the appearance of visual relations is always subtle and can be described by multiple predicate words from different perspectives, e.g., “ride” can be depicted as “race” and “sit on”, from the sports and spatial position views, respectively. To this end, we propose to model visual relations as continuous embeddings, and design diffusion models to achieve …

Do Developers Read Type Information? An Eye-Tracking Study On Typescript, Samuel W. Flint, Robert Dyer, Bonita Sharif

Research & Publications

Statically-annotated types have been shown to aid developers in a number of programming tasks, and this benefit holds true even when static type checking is not used. It is hypothesized that this is because developers use type annotations as in-code documentation. In this study, we aim to provide evidence that developers use type annotations as in-code documentation. Understanding this hypothesized use will help to understand how, and in what contexts, developers use type information; additionally, it may help to design better development tools and inform educational decisions. To provide this evidence, we conduct an eye tracking study with 26 undergraduate …

Distilling The Complexity Of Agent-Based Simulations Into Textual Explanations Via Large Language Models, Noé Y. Flandre, Philippe J. Giabbanelli

VMASC Publications

Communicating the design and results of agent-based models (ABMs) to subject matter experts is challenging, which hinders participation and limits trust in simulation-based decision support. Large language models (LLMs) can communicate ABMs as textual summaries, thus complementing traditional disclosure through statistical and visualization techniques. While prior work translated the structure of conceptual models into narratives via LLMs, our extension covers the dynamics of simulation models via an automated simulation-to-text method that extracts contextual information from NetLogo ABMs, performs repeated simulations, and generates narrative descriptions (including the model’s purpose, parameters, and simulation dynamics) using mutimodal LLMs. Furthermore, four summarization algorithms spanning …

Llm-Driven Weekly Newsletter To Assess Open Source Software Project Github Health, Christian Novalski, Christopher Chavez, Ghalian Fayyadh, Kostadin Damevski

Undergraduate Research Posters

Open Source Software (OSS) projects increasingly depend on a diverse set of contributors, including episodic participants who contribute intermittently. Episodic contributors represent a large portion of OSS communities, yet projects often struggle to retain them, leading to decreased project health and continuity. While dashboards and real-time communication tools support continuously active contributors, they often fail to serve the unique needs of episodic participants, who may struggle to remain informed and re-engage with project activity after periods of absence. In this study, we examine the effect of a weekly, email-based newsletter intervention designed to improve awareness and engagement among episodic OSS …

Deep Learning Approaches For Voltammetric Analysis Of Coffee, Ryan Koes

Honors Theses

This thesis investigates deep learning approaches for voltammetric analysis of brewed coffee using a low-cost electrochemical system and screen-printed electrodes (SPEs). Traditional analytical methods, such as high-performance liquid chromatography (HPLC) and gas chromatography-mass spectrometry (GC-MS), provide precise quantification of key compounds but require expensive instrumentation and specialized expertise, limiting accessibility. While SPEs offer a more accessible alternative, they yielded poor results with traditional processing; however, when combined with a neural network, the system proved more effective. In experiments with 132 coffee samples, mean errors for caffeine, CGA, and TDS predictions were 52.98 ppm, 70.48 ppm, and 0.08%, respectively. These findings …

A Web-Based Wizard-Of-Oz Platform For Collaborative And Reproducible Human-Robot Interaction Research, Sean O'Connor

Honors Theses

The Wizard-of-Oz (WoZ) technique is widely used in Human-Robot Interaction (HRI) research, but two persistent problems limit its effectiveness: existing tools impose technical barriers that exclude non-engineering domain experts (the Accessibility Problem), and the fragmented landscape of robot-specific implementations makes interaction scripts difficult to port across platforms (the Reproducibility Problem- concerning execution consistency and portability, not third-party replication). Through a literature review, I identified three design principles to address both: a hierarchical specification model, an event-driven execution model, and a plugin architecture that decouples experiment logic from robot-specific implementations. I realized these principles in HRIStudio, an open-source, web-based platform providing …

An Empirical Framework For Evaluating Semantic Preservation Using Hugging Face, Nan Jia, Anita Raja, Raffi Khatchadourian

Publications and Research

As machine learning (ML) becomes an integral part of high-autonomy systems, it is critical to ensure the trustworthiness of learning-enabled software systems (LESS). Yet, the nondeterministic and run-time-defined semantics of ML complicate traditional software refactoring. We define semantic preservation in LESS as the property that optimizations of intelligent components do not alter the system's overall functional behavior. This paper introduces an empirical framework to evaluate semantic preservation in LESS by mining model evolution data from HuggingFace. We extract commit histories, $\textit{Model Cards}$, and performance metrics from a large number of models. To establish baselines, we conducted case studies in three …

Printer For Music Box, Chad Lewis, Caleb Murawski, Zion Smith, Bryan Tibbs

Williams Honors College, Honors Research Projects

The traditional method of creating music box sheet music involves manually punching holes into a paper strip using a hand-operated hole punch. This process involves precise knowledge of each note’s location and the ability to achieve perfect accuracy for hours.

The goal of this system is to automate this process, significantly reducing the time required while greatly improving the accuracy of the resulting music box playback. The user simply uploads a MIDI file of their choice into a user-friendly application. Here, the file is modified based on the user’s needs and sent to an automated hole-punching system to punch the …

A Decade Of Programming Languages: Trends In Popularity And Influence, Jonathan C. Erb

Williams Honors College, Honors Research Projects

Programming languages play a central role in open-source software ecosystems, yet their adoption, visibility, and influence shift over time as technologies, developer communities, and industry practices evolve. The study aims to investigate long-term trends in programming-language usage on GitHub from 2014 through 2024, focusing on ten major languages that represent diverse domains and ecosystems. Using repository metadata, engagement metrics such as stars and forks, and language-level code statistics measured with cloc, the analysis will examine changes in repository creation, code contribution volume, and popularity. Since popularity remains an unsettled and multidimensional concept, part of this research involves determining how it …

Do Comments And Expertise Still Matter? An Experiment On Programmers’ Adoption Of Ai-Generated Javascript Code, Changwen Li, Christoph Treude, Ofir Turel

Research Collection School Of Computing and Information Systems

This paper investigates the factors influencing programmers’ adoption of AI-generated JavaScript code recommendations within the context of lightweight, function-level programming tasks. It extends prior research by (1) utilizing objective (as opposed to the typically self-reported) measurements for programmers’ adoption of AI-generated code and (2) examining whether AI-generated comments added to code recommendations and development expertise drive AI-generated code adoption. We tested these potential drivers in an online experiment with 173 programmers. Participants were asked to answer some questions to demonstrate their level of development expertise. Then, they were asked to solve a LeetCode problem without AI support. After attempting to …

Gui Test Migration Via Abstraction And Concretization, Yakun Zhang, Chen Liu, Xiaofei Xie, Yun Lin, Jin Song Dong, Dan Hao, Lu Zhang

Research Collection School Of Computing and Information Systems

GUI test migration aims to produce test cases with events and assertions to test specific functionalities of a target app. Existing migration approaches typically focus on the widget-mapping paradigm that maps widgets from source apps to target apps. However, since different apps may implement the same functionality in different ways, direct mapping may result in incomplete or buggy test cases, thus significantly impacting the effectiveness of testing the target functionality and the practical applicability of migration approaches.In this article, we propose a new migration paradigm (i.e., the abstraction-concretization paradigm) that first abstracts the test logic for the target functionality and …

Dual-Lora And Quality-Enhanced Pseudo Replay For Multimodal Continual Food Learning, Xinlan Wu, Bin Zhu, Feng Han, Pengkun Jiao, Jingling Chen

Research Collection School Of Computing and Information Systems

Food analysis has become increasingly critical for health-related tasks such as personalized nutrition and chronic disease prevention. However, existing large multimodal models (LMMs) in food analysis suffer from catastrophic forgetting when learning new tasks, requiring costly retraining from scratch. To address this, we propose a novel continual learning framework for multimodal food learning, integrating a Dual-LoRA architecture with Quality-Enhanced Pseudo Replay. We introduce two complementary low-rank adapters for each task: a specialized LoRA that learns task-specific knowledge with orthogonal constraints to previous tasks’ subspaces, and a cooperative LoRA that consolidates shared knowledge across tasks via pseudo replay. To improve the …

Algorithmic Trading In Idiosyncratic-Payoff Markets: A Multi-Agent System For On-Chain Prediction Contracts, Saif Aldeen A.K. Agha

CMC Senior Theses

This thesis documents the design, deployment, and forward-test evaluation of an evolutionary multi-agent algorithmic trading system on Polymarket, the largest decentralized prediction market. The system pairs a locally-hosted 72-billion-parameter language model with a gradient-boosted statistical filter and an evolutionary selection mechanism that maintains a population of approximately 500 autonomous trading agents. Each agent generates a probability estimate for an event, compares it to the prevailing market price, and trades the resulting disagreement.

The central empirical exercise estimates a panel regression of trade-level profit on the absolute disagreement between the agent's probability estimate and the market price, controlling for agent identity, …