Digital Commons Network^™

Collaborative Tree Search For Enhancing Embodied Multi-Agent Collaboration, Lizheng Zu, Lin Lin, Song Fu, Na Zhao, Pan Zhou

Research Collection School Of Computing and Information Systems

Embodied agents based on large language models (LLMs) face significant challenges in collaborative tasks, requiring effective communication and reasonable division of labor to ensure efficient and correct task completion. Previous approaches with simple communication patterns carry erroneous or incoherent agent actions, which can lead to additional risks. To address these problems, we propose Cooperative Tree Search (CoTS), a framework designed to significantly improve collaborative planning and task execution efficiency among embodied agents. CoTS guides multi-agents to discuss long-term strategic plans within a modified Monte Carlo tree, searching along LLMdriven reward functions to provide a more thoughtful and promising approach to …

A Knowledge Enhanced Large Language Model For Bug Localization, Yue Li, Bohan Liu, Ting Zhang, Zhiqi Wang, David Lo, Lanxin Yang, Jun Lyu, He Zhang

Research Collection School Of Computing and Information Systems

A significant number of bug reports are generated every day as software systems continue to develop. Large Language Models (LLMs) have been used to correlate bug reports with source code to locate bugs automatically. The existing research has shown that LLMs are effective for bug localization and can increase software development efficiency. However, these studies still have two limitations. First, these models fail to capture context information about bug reports and source code. Second, these models are unable to understand the domain-specific expertise inherent to particular projects, such as version information in projects that are composed of alphanumeric characters without …

Efficient And Green Large Language Models For Software Engineering: Literature Review, Vision, And The Road Ahead, Jieke Shi, Zhou Yang, David Lo

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have recently shown remarkable capabilities in various software engineering tasks, spurring the rapid growth of the Large Language Models for Software Engineering (LLM4SE) area. However, limited attention has been paid to developing efficient LLM4SE techniques that demand minimal computational cost, time, and memory resources, as well as green LLM4SE solutions that reduce energy consumption, water usage, and carbon emissions. This article aims to redirect the focus of the research community toward the efficiency and greenness of LLM4SE, while also sharing potential research directions to achieve this goal. It commences with a brief overview of the significance …

Deepvec: State-Vector Aware Test Case Selection For Enhancing Recurrent Neural Network, Zhonghao Jiang, Meng Yan, Li Huang, Weifeng Sun, Chao Liu, Song Sun, David Lo

Research Collection School Of Computing and Information Systems

Deep Neural Networks (DNN) have realized significant achievements across various application domains. There is no doubt that testing and enhancing a pre-trained DNN that has been deployed in an application scenario is crucial, because it can reduce the failures of the DNN. DNN-driven software testing and enhancement require large amounts of labeled data. The high cost and inefficiency caused by the large volume of data of manual labeling, and the time consumption of testing all cases in real scenarios are unacceptable. Therefore, test case selection technologies are proposed to reduce the time cost by selecting and only labeling representative test …

Advancing Academic Advising With Knowledge Graphs: Integrating Machine Learning And Llms For Personalized Course Planning, Sara Alshamsi

Theses

Academic advising plays a critical role in helping students make informed decisions, improve academic performance, and successfully navigate their university journey. However, with increasing university enrollment, traditional advising methods often struggle to scale, leading to student frustration and overburdened advisors. Additionally, designing course offerings that match student demand is a complex and error-prone process involving multiple stakeholders. To address these challenges, this thesis proposes an automated, data-driven system for generating personalized academic plans for students. The primary aim of this thesis is to develop a system that reduces students’ dependency on advisors while simultaneously providing accurate estimates of course demand …

Advancing Fake News Detection With Graph Neural Network And Deep Learning, Haji Gul, Feras Al-Obeidat, Muhammad Wasim, Adnan Amin, Fernando Moreira

All Works

In the modern era of digital technology, the rapid distribution of news via social media platforms substantially contributes to the propagation of false information, presenting challenges in upholding the accuracy and reliability of information. This study presents an updated approach that utilizes graph neural networks (GNNs) alongside with advanced deep learning techniques to improve the identification of false information. In contrast to traditional approaches that primarily rely on analyzing text and assessing the credibility of sources, our methodology utilizes the structural information of news propagation networks. This allows for a detailed comprehension of the interconnections and patterns that are indicative …

Chatgpt’S Performance Evaluation In Spreadsheets Modeling To Inform Assessments Redesign, Michelle L. F. Cheong

Research Collection School Of Computing and Information Systems

Background: Increasingly, students are using ChatGPT to assist them in learning and even completing their assessments, raising concerns of academic integrity and loss of critical thinking skills. Many articles suggested educators to redesign assessments which are more “Generative-AI-resistant” and to focus on assessing students on higher order thinking skills. However, there is a lack of articles that attempt to quantify assessments at different cognitive levels to provide empirical study insights on ChatGPT’s performance at different levels, which will affect how educators redesign their assessments.Objectives: Educators need new information on how well ChatGPT performs to redesign future assessments to assess their …

Alayadb: The Data Foundation For Efficient And Effective Long-Context Llm Inference, Yangshen Deng, Zhengxin You, Long Xiang, Qilong Li, Peiqi Yuan, Zhaoyang Hong, Yitao Zheng, Wanting Li, Runzhong Li, Haotian Liu, Kyriakos Mouratidis, Man Lung Yiu, Huan Li, Qiaomu Shen, Rui Mao, Bo Tang

Research Collection School Of Computing and Information Systems

AlayaDB is a cutting-edge vector database system natively architected for efficient and effective long-context inference for Large Language Models (LLMs) at AlayaDB AI. Specifically, it decouples the KV cache and attention computation from the LLM inference systems, and encapsulates them into a novel vector database system. For the Model as a Service providers (MaaS), AlayaDB consumes fewer hardware resources and offers higher generation quality for various workloads with different kinds of Service Level Objectives (SLOs), when compared with the existing alternative solutions (e.g., KV cache disaggregation, retrieval-based sparse attention). The crux of AlayaDB is that it abstracts the attention computation …

Reaccept: Automated Co-Evolution Of Production And Test Code Based On Dynamic Validation And Large Language Models, Jianlei Chi, Xiaotian Wang, Yuhan Huang, Lechen Yu, Di Cui, Jianguo Sun, Jun Sun

Research Collection School Of Computing and Information Systems

Synchronizing production and test code, known as PT co-evolution, is critical for software quality. Given the significant manual effort involved, researchers have tried automating PT co-evolution using predefined heuristics and machine learning models. However, existing solutions are still incomplete. Most approaches only detect and flag obsolete test cases, leaving developers to manually update them. Meanwhile, existing solutions may suffer from low accuracy, especially when applied to real-world software projects. In this paper, we propose ReAccept, a novel approach leveraging large language models (LLMs), retrievalaugmented generation (RAG), and dynamic validation to fully automate PT co-evolution with high accuracy. ReAccept employs an …

De-Duplicating Silent Compiler Bugs Via Deep Semantic Representation, Junjie Chen, Xingyu Fan, Chen Yang, Shuang Liu, Jun Sun

Research Collection School Of Computing and Information Systems

The compiler bug duplication problem (where many test failures are caused by the same compiler bug) can lead to huge waste of time and resource in diagnosing test failures produced by compiler testing. It is particularly challenging with regard to the silent compiler bugs that do not produce any error messages. To address this problem, multiple white-box techniques were proposed, but they are inapplicable in many practical scenarios. Black-box techniques are more practical, but the existing ones are less effective as they often rely on irrelevant syntactic information. To bridge this gap, we propose a novel black-box technique (BLADE), which …

A Comprehensive Study Of Oop-Related Bugs In C++ Compilers, Bo Wang, Chong Chen, Junjie Chen, Bowen Xu, Chen Ye, Youfang Lin, Guoliang Dong, Jun Sun

Research Collection School Of Computing and Information Systems

Modern C++, a programming language characterized by its extensive use of object-oriented programming (OOP) features, is widely used for system programming. However, C++ compilers often struggle to correctly handle these sophisticated OOP features, resulting in numerous high-profile compiler bugs that can lead to crashes or miscompilation. Despite the significance of OOP-related bugs, existing studies largely overlook OOP features, hindering their ability to discover such bugs. To assist both compiler fuzzer designers and compiler developers, we conduct a comprehensive study of the compiler bugs caused by incorrectly handling C++ OOP-related features. First, we systematically extract 788 OOP-related C++ compiler bugs from …

Hd-Epic: A Highly-Detailed Egocentric Video Dataset, Toby Perrett, Ahmad Darkhalil, Saptarshi Sinha, Omar Emara, Sam Pollard, Kranti Kumar Parida, Kaiting Liu, Prajwal Gatti, Siddhant Bansal, Kevin Flanagan, Jacob Chalk, Zhifan Zhu, Rhodri Guerrier, Fahd Abdelazim, Bin Zhu, Davide Moltisanti, Michael Wray, Hazel Doughty, Dima Damen

Research Collection School Of Computing and Information Systems

We present a validation dataset of newly-collected kitchenbased egocentric videos, manually annotated with highly detailed and interconnected ground-truth labels covering: recipe steps, fine-grained actions, ingredients with nutritional values, moving objects, and audio annotations. Importantly, all annotations are grounded in 3D through digital twinning of the scene, fixtures, object locations, and primed with gaze. Footage is collected from unscripted recordings in diverse home environments, making HDEPIC the first dataset collected in-the-wild but with detailed annotations matching those in controlled lab environments. We show the potential of our highly-detailed annotations through a challenging VQA benchmark of 26K questions assessing the capability to …

Dupin: A Parallel Framework For Densest Subgraph Discovery In Fraud Detection On Massive Graphs, Jiaxin Jiang, Siyuan Yao, Yuchen Li, Qiange Wang, Bingsheng He, Min Chen

Research Collection School Of Computing and Information Systems

Detecting fraudulent activities in financial and e-commerce transaction networks is crucial. One effective method for this is Densest Subgraph Discovery (DSD). However, deploying DSD methods in production systems faces substantial scalability challenges due to the predominantly sequential nature of existing methods, which impedes their ability to handle large-scale transaction networks and results in significant detection delays. To address these challenges, we introduce Dupin, a novel parallel processing framework designed for efficient DSD processing in billion-scale graphs. Dupin is powered by a processing engine that exploits the unique properties of the peeling process, with theoretical guarantees on detection quality and efficiency. …

Community Detection In Heterogeneous Information Networks Without Materialization, Jiaxin Jiang, Siyuan Yao, Yuhang Chen, Bingsheng He, Yudong Niu, Yuchen Li, Shixuan Sun, Yongchao Liu

Research Collection School Of Computing and Information Systems

Community detection in heterogeneous information networks (HINs) poses significant challenges due to the diversity of entity types and the complexity of their interrelations. While traditional algorithms may perform adequately in some scenarios, many struggle with the high memory usage and computational demands of large-scale HINs. To address these challenges, we introduce a novel framework, SCAR, which efficiently uncovers community structures in HINs without requiring network materialization. SCAR leverages insights from meta-paths to interpret multi-relational data through compact vertex-based sketches, significantly reducing computational overhead and materialization overhead. We propose a sketch-based technique for estimating changes in modularity, improving both the precision …

Large Language Model For Vulnerability Detection And Repair: Literature Review And The Road Ahead, Xin Zhou, Sicong Cao, Xiaobing Sun, David Lo

Research Collection School Of Computing and Information Systems

The significant advancements in Large Language Models (LLMs) have resulted in their widespread adoption across various tasks within Software Engineering (SE), including vulnerability detection and repair. Numerous studies have investigated the application of LLMs to enhance vulnerability detection and repair tasks. Despite the increasing research interest, there is currently no existing survey that focuses on the utilization of LLMs for vulnerability detection and repair. In this paper, we aim to bridge this gap by offering a systematic literature review of approaches aimed at improving vulnerability detection and repair through the utilization of LLMs. The review encompasses research work from leading …

Keep The Balance: A Parameter-Efficient Symmetrical Framework For Rgb+X Semantic Segmentation, Jiaxin Cai, Jingze Su, Qi Li, Wenjie Yang, Shu Wang, Tiesong Zhao, Shengfeng He, Wenxi Liu

Research Collection School Of Computing and Information Systems

Multimodal semantic segmentation is a critical challenge in computer vision, with early methods suffering from high computational costs and limited transferability due to full fine-tuning of RGB-based pre-trained parameters. Recent studies, while leveraging additional modalities as supplementary prompts to RGB, still predominantly rely on RGB, which restricts the full potential of other modalities. To address these issues, we propose a novel symmetric parameter-efficient fine-tuning framework for multimodal segmentation, featuring with a modality-aware prompting and adaptation scheme, to simultaneously adapt the capabilities of a powerful pre-trained model to both RGB and X modalities. Furthermore, prevalent approaches use the global cross-modality correlations …

Towards Uncertainty Aware Task Delegation And Human-Ai Collaborative Decision-Making, Min Hun Lee, Martyn Zhe Yu Tok

Research Collection School Of Computing and Information Systems

Despite the growing promise of artificial intelligence (AI) in supporting decision-making across domains, fostering appropriate human reliance on AI remains a critical challenge. In this paper, we investigate the utility of exploring distance-based uncertainty scores for task delegation to AI and describe how these scores can be visualized through embedding representations for human-AI decision-making. After developing an AI-based system for physical stroke rehabilitation assessment, we conducted a study with 19 health professionals and 10 students in medicine/health to understand the effect of exploring distance-based uncertainty scores on users’ reliance on AI. Our findings showed that distance-based uncertainty scores outperformed traditional …

Event-Based Eye Tracking: Event-Based Vision Workshop 2025, Qinyu Chen, Et. Al.

Research Collection School Of Computing and Information Systems

No abstract provided.

On Lexicographic Proof Rules For Probabilistic Termination, Krishnendu Chatterjee, Ehsan Kafshdar Goharshady, Petr Novotný, Jiří Zárevucký, Dorde Zikelic

Research Collection School Of Computing and Information Systems

We consider the almost-sure (a.s.) termination problem for probabilistic programs, which are a stochastic extension of classical imperative programs. Lexicographic ranking functions provide a sound and practical approach for termination of non-probabilistic programs, and their extension to probabilistic programs is achieved via lexicographic ranking supermartingales (LexRSMs). However, LexRSMs introduced in the previous work have a limitation that impedes their automation: all of their components have to be non-negative in all reachable states. This might result in a LexRSM not existing even for simple terminating programs. Our contributions are twofold. First, we introduce a generalization of LexRSMs that allows for some …

Unlocking The Power Of Socio-Knowledge Association For Enterprise Risk Identification In Stock Market, Zhenghao Liu, Keng Siau, Shaochen Yang, Feicheng Ma

Research Collection School Of Computing and Information Systems

Potential risk signals reflected in supply chain and equity connections between enterprises and social connections between investors are becoming crucial to identifying enterprise risks in addition to basic financial indicators. Traditional risk management systems face challenges in adapting to these complexities, highlighting the need for a proactive paradigm shift in risk management. Leveraging graph models such as social networks and knowledge graphs offers a promising approach to identifying and managing potential associated risks effectively. To bridge existing research gaps, a novel risk identification framework driven by social-knowledge graphs has been proposed, integrating graph deep learning and reinforcement learning techniques guided …

Large Language Models For Logical Fallacy Detection, Nicole Anne Hui-Ying Teo, Donghao Huang, Erik Cambria, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Identifying logical fallacies is essential for maintaining log-ical reasoning and reducing false information in a variety of domains, such as the media, law, and education. We present an extensive study on the use of large language models (LLMs) for logical fallacy detection and provide a comparative overview of model performance across various fallacy classes. We evaluate the logical fallacy detection capabilities of multiple state-of-the-art models (LLaMA, Qwen, Gemma, Phi) utilizing accuracy, precision, recall, and F1-score as assessment measures. Accord-ing to our findings, our models do well on simple fallacies like “circular reasoning,” but they have trouble with more interpretive reasoning …

Property Testing Ai: An Efficient Frontier, Paul Sopher Lintilhac

Dartmouth College Ph.D Dissertations

In this dissertation, we take a step towards addressing the major problem of a lack of standardized and rigorous approaches to testing and evaluation of AI systems. Taking inspiration from both the fields of Property Testing and Property Based Testing (for programs), we develop a novel taxonomy of partially overlapping classes of properties of AI systems, including simple properties, compound properties, higher order properties, data relation properties, and architecture-utility properties. We argue that this taxonomy categorizes a diverse set of AI traits -- including accuracy, fairness, robustness, monotonicity, point-wise and global privacy properties, sensitivity, and more -- according to the …

Optical Character Recognition For Early Handwriting Legibility Assessment, Franceli L. Cibrian, Kayla Anderson, Yingying 'Yuki' Chen, Lauren Min, Lizbeth Escobedo

Engineering Faculty Articles and Research

Monitoring children’s handwriting, such as avoiding writing assignments, displaying uneven letter formation, or showing slow writing speed, can help identify developmental and academic issues early. Poor handwriting affects up to 34% of children, leading to academic and self-esteem challenges. Handwriting assessments, typically conducted by teachers, are often delayed due to workload and could be subjective and inconsistent. This paper explores the potential of Optical Character Recognition (OCR) technology to augment and ease handwriting assessments. Based on an evaluation of 10 OCR algorithms using 33 handwriting samples assessed by two experts, the research indicates that Pen to Print and Google are …

Tracing My Roots: An Exploratory Data Visualization And Analysis Of Jewish Immigration And Assimilation To New York City, Jamie E. Gelberg

Dissertations, Theses, and Capstone Projects

As my Capstone, I explored the complex process of immigrant assimilation to New York City from the late 19th century and beyond through a personal lens, using my Ashkenazi Jewish family as a case study.

I outlined and analyzed relevant demographic data from the US Census Bureau, Berman Jewish DataBank, and other sources to understand New York City during this period and how Jewish immigrants fit into the story. I focused on my family history, immigration and settlement, social assimilation, and economic status. I also incorporated personal narratives from my family history from 3 generations. These narratives help provide context …

Sla Evaluation And Composition In Reconfigurable Cloud-Based Services, Michael Iannelli

Dissertations, Theses, and Capstone Projects

Given the business model of offering data and computing services in a cloud setting, a major question arises: How do the services of one cloud provider compare to those of others? With the ubiquitous use of smartphones and tablets, the ability of a cloud provider to support QoS and client mobility becomes paramount. This research proposes a methodology for evaluating service-level agreements (SLAs) between cloud providers and their consumers, with a particular focus on dynamic SLA composition to adapt to changes in the application requirements and the external environment—such as traffic surges, security threats, or evolving business models.

In one …

On The Design Of A Framework For Large-Scale Exploratory Graph Analytics, Oliver Andres Alvarado Rodriguez

Dissertations

Large-scale exploratory graph analytics merges data science with high-performance computing to extract critical insights from network-representable data. Data scientists routinely analyze data from the natural, social, and computing sciences by representing it as networks, or graphs, where objects become vertices and their relationships become edges. This representation allows data scientists to add graph analytics to their toolbox. However, designing tools for large-scale exploratory graph analytics is challenging due to the complexities of graph algorithms, such as high communication in distributed systems and large memory demands. These challenges can lead to overly complex software, which limits usability and development to a …

Machine Learning And Optimization For Intelligent Decision-Making, Elson Cibaku

Dissertations

This dissertation presents a series of innovative machine learning and optimization model designs that address complex operational challenges across logistics and power systems. By integrating advanced neural architectures with robust optimization techniques, the work delivers scalable solutions designed to improve efficiency, reliability, and decision-making in dynamic and real-world environments. The first study introduces a two-stage approach to effective vaccine distribution. This framework tackles the capacitated vehicle routing problem by combining adaptive clustering techniques with reinforcement learning and a simulated annealing pickup policy. Through extensive computational experiments, the approach demonstrates substantial improvements in routing efficiency, reducing both computational time and logistical …

Adversarial Robustness In Advanced Machine Learning Models Integrating Graph Neural Networks And Large Language Models, Mahmoud Nazzal

Dissertations

Artificial intelligence (AI) has achieved remarkable performances across various domains. In most real-world applications, data often takes relational forms, such as graphs and networks, or sequential forms, such as text and time series. As AI evolves, specialized models have emerged to handle these structures; Graph Neural Networks (GNNs) for relational mining and Large Language Models (LLMs) for sequential understanding. Despite their success, these models face challenges in security, robustness, and interpretability. GNNs excel in relational reasoning but are vulnerable to adversarial manipulation and lack interpretability, while LLMs are strong in linguistic reasoning and generalization yet struggle with relational data and …

Fact-Checking As A Multi-Step Process: From Ambiguity Resolution To Claim Validation, Wenbo Wang

Dissertations

The spread of misinformation and disinformation has become a major concern, particularly with the rise of social media as a primary source of information for many people. Fact-checking—the process of verifying claims against credible evidence—has emerged as a critical safeguard against misinformation. Yet, the task is fraught with challenges: claims are often ambiguous, context-dependent, or composed of multiple intertwined assertions, while automated systems struggle to replicate the nuanced reasoning of human experts. This dissertation addresses these challenges by reimagining fact-checking as a multi-step, knowledge-guided process that systematically resolves ambiguity, decomposes complexity, and validates claims through structured reasoning. Additionally, the proposed …

Enriching Vision Representation By Deep Neural Networks And Self-Supervised Learning, Yucong Shen

Dissertations

Nowadays, more and more interesting computer vision tasks are tackled by deep learning approaches. However, the increasing model complexity imposes significant computational and storage costs. To address this challenge, this dissertation explores efficient deep learning techniques, proposing morphological layer, an efficient feature extraction layer. It achieves competitive image classification accuracy with significantly decreased model parameters. Another attempt at efficient deep learning is a proposed channel pruning approach that compresses deep neural networks by identifying and removing redundant channels using optimal transport theory. This approach achieves significant reductions in model size and computational cost while maintaining or even improving performance across …