Computer Sciences Commons^™

Chatgpt, Can You Generate Multiple-Choice Questions For An Undergraduate Computing Course? An Evaluation Of Its Effectiveness Using Classical Test Theory, Eng Lieh Ouh, Kar Way Tan, Siaw Ling Lo, Benjamin Gan, Yuhao Zhang

Research Collection School Of Computing and Information Systems

Educators are increasingly adopting large language models such as ChatGPT to generate multiple-choice questions (MCQs), yet empirical evidence on the quality of these items in computing education assessments remains limited. This study compares 30 ChatGPT-generated and 30 manually crafted items from an undergraduate software design course, and evaluates item difficulty, discrimination, and distractor quality using Classical Test Theory. We triangulated two evaluations using within-subjects and between-subjects designs. Our quantitative findings show that all three metrics in both evaluations point in the same direction. ChatGPT-generated items are easier, less discriminating, and exhibit poorer distractor quality than manually crafted items. Distractor quality …

Ddor: Delta Debugging For Explainable Overrefusal Testing And Repair, Qinyan Zhou, Peixin Zhang, Jun Sun, Haonan Zhang, Dongxia Wang

Research Collection School Of Computing and Information Systems

While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rejection of benign queries that merely appear risky. We present DDOR (Delta Debugging for OverRefusal), a fully automated and explainable framework for overrefusal testing and repair in a black-box setting, where only model inputs and outputs are accessible and internal safety mechanisms remain opaque. DDOR applies delta debugging to localize minimal refusal-triggering fragments (mRTFs) that provide phrase-level, explainable evidence for why a refusal occurs. Conditioned on these mRTFs, DDOR generates diverse, context-rich prompts and performs multi-oracle validation to filter intrinsically …

Restoring Linguistic Grounding In Vla Models Via Train-Free Attention Recalibration, Ninghao Zhang, Bin Zhu, Shijie Zhou, Jingjing Chen

Research Collection School Of Computing and Information Systems

Vision-Language-Action (VLA) models enable robots to perform manipulation tasks directly from natural language instructions and are increasingly viewed as a foundation for generalist robotic policies. However, their reliability under Out-Of-Distribution (OOD) instructions remains underexplored. In this paper, we reveal a critical failure mode in which VLA policies continue executing visually plausible actions even when the language instruction contradicts the scene. We refer to this phenomenon as linguistic blindness, where VLA policies prioritize visual priors over instruction semantics during action generation. To systematically analyze this issue, we introduce ICBench, a diagnostic benchmark constructed from the LIBERO dataset that probes language–action coupling …

Facevalue: Exploring Real-Time Self-View Overlays To Prompt Meaning-Oriented Self-Awareness In Remote Meetings, Gun Woo (Warren) Park, Anthony Tang, Fanny Chevalier

Research Collection School Of Computing and Information Systems

In remote video meetings, visual non-verbal cues, such as facial expressions or head movements, are seen continuously but often only partially. This increases ambiguity compared to in-person settings and can cause misinterpretation or misalignment between intended and perceived meaning. Motivated by communication theories, we designed FaceValue, a technology probe that augments the self-view with private, real-time overlays. These overlays are subtle, suggestive prompts intended to help attendees reflect on how their cues might be interpreted by others. To invite personal interpretation, FaceValue avoids behavioral labeling and instead aims to support meaning-oriented self-awareness: recognizing when visible cues may unintentionally (mis)communicate intent. …

Bayesian And Multi-Objective Decision Support For Incident Mitigation In Cyber-Physical Systems, Shaofei Huang, Christopher M. Poskitt, Lwin Khin Shar

Research Collection School of Computing and Information Systems

Cyber-physical systems increasingly rely on interconnected physical and digital systems whose security incidents can escalate rapidly into safety and operational failures. Existing decision-support approaches struggle to support incident response because they rely on static assumptions, incomplete vulnerability data, and single-objective risk models that do not adequately capture trade-offs between attack success likelihood, impact severity, and system availability. This paper proposes an adaptive decision-support framework for incident mitigation in cyber-physical systems that integrates hierarchical Bayesian Network modelling, confidence-calibrated exposure estimation, and multi-objective optimisation into a unified, adaptive pipeline. The framework constructs probabilistic models from system architecture and vulnerability data, incorporating complementary …

Towards More Inclusive Ai Systems In Cities, Siew Ying Shee, Orlando Woods

Research Collection School of Social Sciences

Artificial Intelligence (AI) is increasingly embedded in urban infrastructures and governance, shaping how people, spaces, and futures are classified, prioritised, and managed. Yet, most AI systems are developed within a narrow set of linguistic and geopolitical contexts and exported globally, embedding particular epistemic assumptions into diverse urban environments. Even where formal inclusion metrics are met, such asymmetries can render certain populations and realities less legible within algorithmic systems. Prevailing approaches in digital inclusion—centred on fairness metrics, representation, or access—presume technologies as politically inert and bounded. Yet, the adaptive and probabilistic behaviour of contemporary AI disrupts this premise, challenging the idea …

Generalized Logit Adjustment: Improved Fine-Tuning By Mitigating Label Bias In Zero-Shot Vision Models, Beier Zhu, Qianru Sun, Xun Yang, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, fine-tuning and ensembling are also commonly adopted to better fit the downstream tasks. However, we argue that such prior work has overlooked the inherent biases in foundation models. Due to the highly imbalanced Web-scale training set, foundation models are inevitably skewed toward frequent semantics, and thus the subsequent fine-tuning or ensembling is still biased. In this study, we systematically examine the biases in foundation models and demonstrate the efficacy of our proposed Generalized …

Learning 1-Bit Lidar-Based Localization With Auxiliary Objective, Kaijie Yin, Zhiyuan Zhang, Tian Gao, Wentao Zhu, Cheng-Zhong Xu, Hui Kong

Research Collection School Of Computing and Information Systems

6-DoF LiDAR-based localization is a fundamental capability for autonomous systems operating in large-scale outdoor environments. Many deep-learning-based localization methods have achieved promising performance so far. However, as one of the always-on modules competing for limited on-board computational resources, the localization module is expected to consume only a small portion of the overall compute budget. Most existing learning-based methods are still too heavy for this purpose. In contrast, binary neural networks (BNNs) offer an appealing solution, but the 1-bit compression causes severe information loss and performance drop. In this paper, we address this challenge by proposing Binarized LiDAR-based Localization (BiLoc), the …

Smart: When Is It Actually Worth Expanding A Speculative Tree?, Lifu Wang, Pan Zhou

Research Collection School Of Computing and Information Systems

Tree-based speculative decoding accelerates autoregressive generation by verifying a branching tree of draft tokens in a single targetmodel forward pass. However, existing methods prioritize maximizing token-level likelihood or the number of accepted tokens while ignoring a critical “efficiency paradox”: the computational overhead of drafting and verifying big trees can grow super-linearly, particularly at scale. This often leads to negative wall-clock speedup when batch sizes increase or hardware saturation limits are reached. To address this, we propose SMART, a System-aware Marginal Analysis framework for Runtime Tree construction. SMART reformulates tree expansion as a hardware-aware optimization problem that directly maximizes end-toend speedup. …

Prune: A Patching Based Repair Framework For Certifiable And Privacy-Robust Unlearning Of Neural Networks, Xuran Li, Jingyi Wang, Xiaohan Yuan, Peixin Zhang

Research Collection School Of Computing and Information Systems

Machine unlearning has emerged as a key mechanism for enabling the “right to be forgotten” in neural network models, allowing the selective removal of specific training data upon request. Existing approaches typically rely on retraining models with the remaining data, which is computationally expensive and difficult to verify, especially when deployed models are distributed or resource-constrained. To address this challenge, our prior conference work introduced PRUNE, a patching-based framework that formulates unlearning as a neural network repair problem. PRUNE achieves targeted forgetting by learning lightweight patch networks that redirect model predictions on the data to be unlearned while preserving performance …

Neural Symphony Of Flow Experience: Evidence For High-Dimensional Metastable Dynamics, Abdelrahman B. M. Eldaly, Kris Zhangguang Kang, Fiona Fui-Hoon Nah, Leanne Lai-Hang Chan, Keng Siau, Xiao Fan Liu, Richard Huskey, Langtao Chen, Tejaswini Yelamanchili, Rene Weber

Research Collection School Of Computing and Information Systems

Flow, an optimal experience characterized by deep immersion and engagement in an activity, has been extensively studied in behavioral research. However, its neural dynamic mechanism remains poorly understood. In a within-subject video gaming experiment, we captured neural activity underlying flow, boredom, and anxiety using a 64-channel electroencephalogram (EEG) system. Compared to boredom and anxiety, flow exhibits the highest global functional connectivity, metastability, and dimensionality of dynamic functional connectivity patterns, suggesting that flow is a highly adaptable process that is supported by high-dimensional neural dynamics. Unlike previous studies that focused on identifying static or localized brain activity, we examine the neural …

Analysis Of Extended Producer Responsibility In E-Waste Management: Policy Drivers And Challenges In Singapore, Aldy Gunawan, Aidan Marc Wong, Tasaporn Visawameteekul, Minh Phuong Huynh, Linh Chi Tran

Research Collection School Of Computing and Information Systems

This paper examines the role of the Extended Producer Responsibility (EPR) scheme in electronic waste (e-waste) management in Singapore. It investigates the policy drivers and challenges of e-waste management, using data from an online survey to explore the attitudes and behaviors of young consumers, with a particular focus on youth. We employ the Theory of Reasoned Action (TRA) and the Theory of Planned Behavior (TPB) frameworks to develop a model that examines the relationships among attitudes, perceived norms, awareness, and perceived convenience in relation to EPR awareness and perception. The findings highlight the need for customized policies tailored to different …

Autoqresearch: Llm-Guided Closed-Loop Policy Search For Adaptive Variational Quantum Optimization, Monit Sharma, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Configuring variational quantum algorithms for combinatorial optimization remains a difficult, expert-driven process requiring coordinated choices over solver family, ansatz, objective, and optimizer. We present AutoQResearch, an LLM-guided closed-loop experimentation framework that casts this task as sequential policy search over a curated design space. Instead of a single static configuration, the framework searches for adaptive solver-control policies that condition future decisions on diagnostics such as feasibility, optimality gap, and convergence stagnation.The system operates through a structured workflow: an LLM agent edits a small policy surface under a fixed evaluation harness, candidate policies are screened using cheap scout evaluations, and only the …

Llm-As-A-Judge For Software Engineering: Literature Review, Vision, And The Road Ahead, Junda He, Jieke Shi, Terry Yue Zhuo, Christoph Treude, Jiamou Sun, Zhenchang Xing, Xiaoning Du, David Lo

Research Collection School Of Computing and Information Systems

The rapid integration of Large Language Models (LLMs) into software engineering (SE) has revolutionized tasks from code generation to program repair, producing a massive volume of software artifacts. This surge in automated creation has exposed a critical bottleneck: the lack of scalable and reliable methods to evaluate the quality of these outputs. Human evaluation, while effective, is very costly and time-consuming. Traditional automated metrics like BLEU rely on high-quality references and struggle to capture nuanced aspects of software quality, such as readability and usefulness. In response, the LLM-as-a-Judge paradigm, which employs LLMs for automated evaluation, has emerged. This approach leverages …

Efficient Test-Time Retrieval Augmented Generation, Hailong Yin, Bin Zhu, Jingjing Chen, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Although Large Language Models (LLMs) demonstrate significant capabilities, their reliance on parametric knowledge often leads to inaccuracies. Retrieval Augmented Generation (RAG) mitigates this by incorporating external knowledge, but these methods may introduce irrelevant retrieved documents, leading to inaccurate responses. While the integration methods filter out incorrect answers from multiple responses, but lack external knowledge like RAG methods, and their high costs require balancing overhead with performance gains. To address these issues, we propose an Efficient Test-Time Retrieval-Augmented Generation Framework named ET2RAG to improve the performance of LLMs while maintaining efficiency. Specifically, ET2RAG is a training-free method, that first retrieves the …

Continuous Query For Top-K Maximal Sum Intervals Over Streaming Data, Zhongshuai Zhang, Xiaochun Yang, Baihua Zheng, Rui Zhu, Haomin Li, Bin Wang

Research Collection School Of Computing and Information Systems

The continuous identification of top-k maximal sum intervals using a sliding window over a data stream is a critical operation for applications in IoT and beyond. A maximal sum interval is a non-overlapping, contiguous subsequence with the maximal sum in a sequence of signed values. Existing algorithms are ill-suited for streaming contexts: they either exhaustively enumerate all intervals even for small k values, or depend on indexes that require frequent and costly restructuring. We propose a novel partition-based strategy. Our core insight is a partitioning scheme that guarantees that any maximal sum interval is fully contained within a single partition, …

Timeradar: A Domain-Rotatable Foundation Model For Time Series Anomaly Detection, Hui He, Hezhe Qiao, Yutong Chen, Kun Yi, Guansong Pang

Research Collection School Of Computing and Information Systems

Current time series foundation models (TSFMs) primarily focus on learning prevalent and regular patterns within a predefined time or frequency domain to enable supervised downstream tasks (\eg, forecasting). Consequently, they are often ineffective for inherently unsupervised downstream tasks—such as time series anomaly detection (TSAD), which aims to identify rare, irregular patterns. This limitation arises because such abnormal patterns can closely resemble the regular patterns when presented in the same time/frequency domain. To address this issue, we introduce TimeRadar, an innovative TSFM built in a fractional time–frequency domain to support generalist TSAD across diverse unseen datasets. Our key insight is that …

Graph Perturbation Analysis For Subgraph Counting, Hanhua Xiao, Yuchen Li, Kyriakos Mouratidis

PhD Student’s Publications Collection

Subgraph counting, which involves determining the frequency of a query graph within a data graph, has numerous applications such as query optimization, fraud detection, and evaluating the expressiveness of graph neural networks. Despite its importance, there has been no systematic study on the impact of adversarial graph perturbations on subgraph counts. In this work, we examine the kSub problem, which aims to identify k edge additions that maximize the count of a query graph. We prove that kSub is intractable due to its NP-hardness, even for constant approximation. To address this, we relax the problem into a top-k selection, termed …

Leading The Change: Staff-Driven Ai Transformation In Smu Libraries’ Collection Team, Siew Khim Lim, Fion Goh

Research Collection Library

No abstract provided.

A Deep Reinforcement Learning Framework For Dynamic Order And Rack Scheduling In Robotic Mobile Fulfillment Systems, Lingjun Wang, Bayi Cheng, Zhiguang Cao, Aldy Gunawan

Research Collection School Of Computing and Information Systems

Robotic mobile fulfillment systems play a vital role in modern e-commerce, but their efficiencydepends on overcoming a critical challenge: coordinating orders and racks effectively under dynamicorder arrivals, diverse delivery deadlines, and resource sharing among multiple stations. This papertackles the resulting dynamic order and rack scheduling problem and proposes an intelligentscheduling framework centred on deep reinforcement learning. At its core is TriNet-PPO, whichtrains a scheduling policy using TriNet, a tripartite graph neural network encoder tailored to capturethe many-to-many relationships among orders, racks, and items. Furthermore, we introduce IPCSA,an integer programming-based cooperative scheduling algorithm that maps station-level actionpreferences to conflict-free joint decisions …

Ai-Ready Libraries Require Ai-Ready Librarians: Building Organisational Capability For Digital Transformation, Salihin Mohammed Ali

Research Collection Library

Academic libraries worldwide are rapidly experimenting with artificial intelligence (AI) to enhance research, learning, discovery, operations, and user engagement. However, many institutions continue to approach AI adoption primarily through isolated pilots, individual experimentation, or technology-centric initiatives. While these efforts generate innovation, they often struggle to scale sustainably without corresponding organisational capability development. This presentation argues that AI-ready libraries require AI-ready librarians and proposes an organisational capability approach for sustainable AI transformation in academic libraries. Drawing from the development of a library-wide AI strategy plans at Singapore Management University, the presentation explores how AI capability-building can be operationalised across diverse functional …

Automated Testing And Enhancement For Autonomous Driving Systems, Mingfei Cheng

Dissertations and Theses Collection (Open Access)

Autonomous Vehicles (AVs) rely on Autonomous Driving Systems (ADSs) to perceive their surroundings, predict the behavior of traffic participants, plan driving actions, and control vehicle motion in complex traffic environments. As AVs move toward large-scale real-world deployment, ADSs are expected not only to avoid collisions and traffic-rule violations, but also to make robust decisions, cooperate effectively with other AVs, and maintain high-quality driving behavior. However, the open, dynamic, and uncertain nature of driving environments makes the systematic testing and enhancement of ADSs a challenging problem.

Although scenario-based testing has made substantial progress in discovering safety-critical violations, several important limitations remain. …

Practical On-Device Intelligence For Resource-Constrained Embedded And Wearable Devices, Xiao Ma

Dissertations and Theses Collection (Open Access)

Embedded and wearable devices increasingly rely on deep neural networks to support intelligent sensing applications directly on the device. However, building practical on-device intelligence remains challenging throughout the deployment lifecycle. Before deployment, models must remain accurate despite severe memory, computation, and energy budgets, and a single device often needs to support multiple sensing applications without deploying a separate model for each application. After deployment, the device continues to operate in changing real-world environments, where shifts in data distribution can degrade the model’s performance over time, so the model must be able to adapt to such shifts efficiently.

The first challenge …

Approximation And Learning-Based Algorithms For Influence Maximization In Multilayer Social Networks, Xueqin Chang, Ruize Liu, Qing Liu, Baihua Zheng, Yunjun Gao

Research Collection School Of Computing and Information Systems

Motivated by the observation that users in the real world often engage across multiple social networks simultaneously, we study the problem of influence maximization in multilayer social networks (Mlim), aiming to select a small set of nodes that maximizes the total influence spread across all layers. To this end, we introduce a hybrid propagation model that jointly captures layer-specific diffusion dynamics and probabilistic cross-layer propagation. Based on this model, we formally define the Mlim problem and establish its NP-hardness, monotonicity, and submodularity. To address the Mlim problem, we first propose a greedy baseline Mlim-Greedy, which achieves a (1-1/e) approximation. Since …

Hvi-Cidnet+: Beyond Extreme Darkness For Low-Light Image Enhancement, Kangbiao Shi, Xiaowen Ma, Yixu Feng, Tao Hu, Peng Wu, Guansong Pang, Qingsen Yan

Research Collection School Of Computing and Information Systems

Low-Light Image Enhancement (LLIE) aims to recover visually pleasing content and details from degraded low-light images. However, existing RGB-based methods often suffer from color bias and brightness artifacts due to inherent high color sensitivity. Although the HSV color space can decouple brightness and color, it introduces noticeable red and black noise artifacts. To address these challenges, we adopt the Horizontal/Vertical-Intensity (HVI) color space for LLIE, which is defined by the HV color map and learnable intensity. The former enforces small distances for red coordinates to alleviate red noise artifacts, while the latter adaptively compresses low-light regions to suppress black noise …

Audeter: A Large-Scale Dataset For Deepfake Audio Detection In Open Worlds, Qizhou Wang, Hanxun Huang, Guansong Pang, Sarah Erfani, Christopher Leckie

Research Collection School Of Computing and Information Systems

Speech synthesis systems can now produce highly realistic vocalisations that pose significant authenticity challenges. Despite substantial progress in deepfake detection models, their real-world effectiveness is often undermined by evolving distribution shifts between training and test data, driven by the complexity of human speech and the rapid evolution of synthesis systems. Existing datasets suffer from limited real speech diversity, insufficient coverage of recent synthesis systems, and heterogeneous mixtures of deepfake sources, which hinder systematic evaluation and open-world model training. To address these issues, we introduce AUDETER (AUdio DEepfake TEst Range), a large-scale and highly diverse deepfake audio dataset comprising over 4,500 …

Left: Learnable Fusion Of Tri-View Tokens For Unsupervised Time Series Anomaly Detection, Dezheng Wang, Tong Chen, Guansong Pang, Congyan Chen, Shihua Li, Hongzhi Yin

Research Collection School Of Computing and Information Systems

As a fundamental data mining task, unsupervised time series anomaly detection (TSAD) aims to build a model for identifying abnormal timestamps without assuming the availability of annotations. A key challenge in unsupervised TSAD is that many anomalies are too subtle to exhibit detectable deviation in any single view (e.g., time domain), and instead manifest as inconsistencies across multiple views like time, frequency, and a mixture of resolutions. However, most cross-view methods rely on feature or score fusion and do not enforce analysis–synthesis consistency, meaning the frequency branch is not required to reconstruct the time signal through an inverse transform, and …

Parameterized Approximation Schemes For Fair Clustering In Doubling Metrics, Xiaoliang Wu, Ting Liang, Zhize Li, Qilong Feng

Research Collection School Of Computing and Information Systems

Fair clustering has garnered considerable attention, with various fairness notions proposed to ensure equitable representation across demographic groups. In this paper, we focus on the k-center problem in bounded doubling metrics under two popular fairness requirements: group fairness and data summarization fairness, referred to Group Fair k-Center (Gf-k-Cen) and Data Summarization Fair k-Center (Dsf-k-Cen), respectively. Both fairness notions extend classical clustering formulation by associating each data point with a demographic label. Motivated by recent advances in parameterized approximation results for fair clustering, we investigate whether these problems admit Fixed-Parameter Tractable (FPT) approximation schemes in bounded doubling metrics. The previous algorithms …

Lessons Learned From The Adrenalin Load Disaggregation Challenge, András Balázs Tolnai, Zheng Ma, Igor Sartori, Clayton Miller, Stephen White, Matt Amos, Gustaf Bengtsson, Akram Hameed, Nørregaard Bo Jørgensen

Research Collection College of Integrative Studies

Crowdsourced data science competitions have emerged as a powerful mechanism for advancing research in energy informatics, offering scalable pathways for developing machine learning solutions that enhance energy efficiency and smart building operations. The ADRENALIN Load Disaggregation Challenge addressed a central problem in energy analytics—non-intrusive load monitoring (NILM) of heating and cooling loads in commercial buildings—while emphasizing the importance of model generalization across different buildings. This paper presents a comprehensive reflection on the lessons learned from organizing and executing the ADRENALIN competition, including technical insights, organizational challenges, and recommendations for future energy data challenges. In addition to the ADRENALIN case, a …

Task-Aligned Haze Removal With Semantic-Aware Fusion And Contrast Self-Correction, Jinbin Wang, Aiping Yang, Guosong Jiang, Wenlong Yu, Dongwei Ren, Qinghua Hu

Research Collection School Of Computing and Information Systems

Adverse haze conditions introduce complex degradations that obscure scene details and distort structural cues critical for object detection, posing persistent challenges for vision‐based sensing systems. Although existing haze removal methods have achieved notable improvements in visual clarity, their optimisation objectives are often misaligned with downstream detection requirements, leading to limited detection performance in real‐world scenarios. To address this issue, this work proposes a task‐aligned weakly supervised haze removal framework, termed Dehaze4Detection, which explicitly aligns low‐level restoration with high‐level detection objectives. The framework incorporates a Semantic‐Aware Multi‐Scale Fusion Module (SMFM) that embeds pixel‐level semantic knowledge into the dehazing process, enabling selective …