Digital Commons Network^™

Sparse-To-Dense: A Free Lunch For Lossless Acceleration Of Video Understanding In Llms, Xuan Zhang, Cunxiao Du, Sicheng Yu, Jiawei Wu, Fengzhuo Zhang, Wei Gao, Qian Liu

Research Collection School Of Computing and Information Systems

Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually very long. We observe that during decoding, the attention scores of most tokens in Video-LLMs tend to be sparse and concentrated, with only certain tokens requiring comprehensive full attention. Based on this insight, we introduce Sparse-to-Dense (StD), a novel decoding strategy that integrates two distinct modules: one leveraging sparse top-K attention and the other employing dense full attention. These modules collaborate to accelerate Video-LLMs without loss. …

Retrieval Augmented Generation For Dynamic Graph Modeling, Yuxia Wu, Lizi Liao, Yuan Fang

Research Collection School Of Computing and Information Systems

Modeling dynamic graphs, such as those found in social networks, recommendation systems, and e-commerce platforms, is crucial for capturing evolving relationships and delivering relevant insights over time. Traditional approaches primarily rely on graph neural networks with temporal components or sequence generation models, which often focus narrowly on the historical context of target nodes. This limitation restricts the ability to adapt to new and emerging patterns in dynamic graphs. To address this challenge, we propose a novel framework, Retrieval-Augmented Generation for Dy namic Graph modeling (RAG4DyG ), which enhances dynamic graph predictions by incorporating contextually and temporally relevant examples from broader …

Information Bottleneck‑Guided Mlps For Robust Spatial‑Temporal Forecasting, Min Chen, Guansong Pang, Wenjun Wang, Cheng Yan

Research Collection School Of Computing and Information Systems

Spatial-temporal forecasting (STF) plays a pivotal role in urban planning and computing. Spatial-Temporal Graph Neural Networks (STGNNs) excel at modeling spatial-temporal dynamics, thus being robust against noise perturbations. However, they often suffer from relatively poor computational efficiency. Simplifying the architectures can improve efficiency but also weakens robustness with respect to noise interference. In this study, we investigate the problem: can simple neural networks such as Multi-Layer Perceptrons (MLPs) achieve robust spatial-temporal forecasting while remaining efficient? To this end, we first reveal the dual noise effect in spatial-temporal data and propose a theoretically grounded principle termed Robust Spatial-Temporal Information Bottleneck (RSTIB), …

Fashiondpo: Fine‑Tune Fashion Outfit Generation Model Using Direct Preference Optimization, Mingzhe Yu, Yunshan Ma, Lei Wu, Changshuo Wang, Xue Li, Lei Meng

Research Collection School Of Computing and Information Systems

Personalized outfit generation aims to construct a set of compatible and personalized fashion items as an outfit. Recently, generative AI models have received widespread attention, as they can generate fashion items for users to complete an incomplete outfit or create a complete outfit. However, they have limitations in terms of lacking diversity and relying on the supervised learning paradigm. Recognizing this gap, we propose a novel framework FashionDPO, which fine-tunes the fashion outfit generation model using direct preference optimization. This framework aims to provide a general fine-tuning approach to fashion generative models, refining a pre-trained fashion outfit generation model using …

What Are Anomalies In A Network?, Kai Ming Ting, Zhong Zhuang, Guansong Pang, Zongyou Liu, Tianrun Liang, Qiuran Zhao

Research Collection School Of Computing and Information Systems

This article examines a collection of assumptions used in the current literature on node anomaly detection in a network. The examination raises the question: What are anomalies in a network? Our attempt to answer this question has provided some interesting findings and led to some open questions. This is the first article which formally defines anomalies in a network and introduces the concept of self-verifiability of a detector without ground-truths in a network. They enable existing detectors to be categorized into two types along the line whether they are self-verifiable or not. We suggest a method to evaluate self-verifiable detectors …

High Frequency Factor Analysis With Partially Observable Factors, Dachuan Chen, Wenqi Lu, Siyu Xie

Research Collection School Of Economics

This paper considers a novel factor structure – Partially Observable Factor Model – where both observable factors and latent factors exist in the model simultaneously. Such factor structure can make sure both interpretability and goodness-of-fit at the same time. Necessary estimation methodologies for this partially observable factor model are developed in this paper for the high frequency data. The proposed estimation methodology is robust to jumps, microstructure noise and asynchronous observation times simultaneously.When the observable factors are exogenous, we provide the estimation theory for the integrated eigenvalues of the residual covariance matrix, which including the bias-corrected estimator, central limit theorem …

Financial Data Stewardship: A Librarian's Approach To Data Discovery And A Call For Coding As A Path To Data Comprehension And Verification, Lip Hwe Tee

Research Collection Library

This conference presentation calls to advocate and emphasise coding as a means to understand datasets, to be able to correctly interpret table structure and relevant fields to extract the correct data, to ensure accuracy and relevance.

Ai Assisted Literature Review Tools For Undergraduates: Restrict, Embrace Or Curate?, Aaron Tay

Research Collection Library

As AI-driven literature review tools become widespread, academic librarians must grapple with a fundamental question—should we ban these tools, selectively curate their use, or embrace them fully? This keynote explores the three competing schools of thought shaping AI’s role in undergraduate literature reviews.

The Restrict school argues that students who have not proven capable of writing quality literature review should be restricted from use of such tools. Much like handing a preschooler a calculator before they understand basic arithmetic will affect the learning of arithmetic, premature use of such tools has the potential to shortcut the research learning process. If …

Runtime Backdoor Detection For Federated Learning Via Representational Dissimilarity Analysis, Xiyue Zhang, Xiaoyong Xue, Xiaoning Du, Xiaofei Xie, Yang Liu, Meng Sun

Research Collection School Of Computing and Information Systems

Federated learning (FL), as a powerful learning paradigm, trains a shared model by aggregating model updates from distributed clients. However, the decoupling of model learning from local data makes FL highly vulnerable to backdoor attacks, where a single compromised client can poison the shared model. While recent progress has been made in backdoor detection, existing methods face challenges with detection accuracy and runtime effectiveness, particularly when dealing with complex model architectures. In this work, we propose a novel approach to detecting malicious clients in an accurate, stable, and efficient manner. Our method utilizes a sampling-based network representation method to quantify …

Nexusgs: Sparse View Synthesis With Epipolar Depth Priors In 3d Gaussian Splatting, Yulong Zheng, Zicheng Jiang, Shengfeng He, Yandu Sun, Junyu Dong, Huaidong Zhang, Yong Du

Research Collection School Of Computing and Information Systems

Neural Radiance Field (NeRF) and 3D Gaussian Splatting (3DGS) have noticeably advanced photo-realistic novel view synthesis using images from densely spaced camera viewpoints. However, these methods struggle in few-shot scenarios due to limited supervision. In this paper, we present NexusGS, a 3DGS-based approach that enhances novel view synthesis from sparse-view images by directly embedding depth information into point clouds, without relying on complex manual regularizations. Exploiting the inherent epipolar geometry of 3DGS, our method introduces a novel point cloud densification strategy that initializes 3DGS with a dense point cloud, reducing randomness in point placement while preventing over-smoothing and overfitting. Specifically, …

A Multimodal Fusion Model Leveraging Mlp Mixer And Handcrafted Features-Based Deep Learning Networks For Facial Palsy Detection, Heng Yim Nicole Oo, Min Hun Lee, Jeong Hoon Lim

Research Collection School Of Computing and Information Systems

Algorithmic detection of facial palsy offers the potential to improve current practices, which usually involve labor-intensive and subjective assessments by clinicians. In this paper, we present a multimodal fusion-based deep learning model that utilizes an MLP mixer-based model to process unstructured data (i.e. RGB images or images with facial line segments) and a feed-forward neural network to process structured data (i.e. facial landmark coordinates, features of facial expressions, or handcrafted features) for detecting facial palsy. We then contribute to a study to analyze the effect of different data modalities and the benefits of a multimodal fusion-based approach using videos of …

Forging The Future, Kenneth Benoit

Asian Management Insights

How AI is rewriting the rules of knowledge, expertise, and practice.

Strategy And Stewardship In An Uncertain World, Havovi Joshi

Asian Management Insights

This issue, as we continue to celebrate Singapore Management University’s (SMU) 25th anniversary, we explore leadership in higher education, the rise of artificial intelligence (AI), ethical stewardship, and other challenges, highlighting how they intersect in our increasingly complex, fast-changing world.

Reducing Carbon Emissions Through Sustainable Food Consumption: Applying An A-S-I Framework On Beijing Residents, Xuan Yang, Jiaxin Zou, Jingyao Gao, Shu Yang

Student Publications

The food sector represents one of the largest contributors to global climate change, making it urgent for the public to transform their food consumption behavior. However, food consumption behaviors that can facilitate carbon reduction, and how to classify these behaviors from the perspective of behavioral science, have not been deeply explored. This study pioneers a novel categorization of carbon-mitigating food consumption behaviors based on an A-S-I framework (i.e., “Avoid” food loss and waste, “Shift” to low-carbon alternatives, and “Improve” dietary structure). Such a classification not only encompasses the full spectrum of emission-altering behaviors but also enables identification of common determinants …

Acquisition Strategy For Innovation Under Competence-Destroying Change: Empirical Study—Pharmaceutical Company's Biotechnology Company Acquisition, Joo Tae Sung

Dissertations and Theses Collection (Open Access)

In response to declining R&D productivity and successive patent cliffs, pharmaceutical companies are increasingly acquiring biotechnology firms to sustain innovation. These acquisitions often occur under conditions of competence-destroying change, where the acquirer's chemistry-based knowledge base does not overlap with the biotechnology expertise of the target, challenging traditional theories that emphasize absorptive capacity and knowledge similarity.
This study introduces therapeutic knowledge, defined as the acquirer’s expertise in specific disease areas, as a distinct and critical dimension that interacts with both chemistry-based and biotechnology-based knowledge. Using a dataset of 212 observations across therapeutic areas from 80 acquisitions, the analysis uncovers an inverted …

On-Demand Scenario Generation For Testing Automated Driving Systems, Songyang Yan, Xiaodong Zhang, Kunkun Hao, Haojie Xin, Yonggang Luo, Jucheng Yang, Ming Fan, Chao Yang, Jun Sun, Zijiang Yang

Research Collection School Of Computing and Information Systems

The safety and reliability of Automated Driving Systems (ADS) are paramount, necessitating rigorous testing methodologies to uncover potential failures before deployment. Traditional testing approaches often prioritize either natural scenario sampling or safety-critical scenario generation, resulting in overly simplistic or unrealistic hazardous tests. In practice, the demand for natural scenarios (e.g., when evaluating the ADS's reliability in real-world conditions), critical scenarios (e.g., when evaluating safety in critical situations), or somewhere in between (e.g., when testing the ADS in regions with less civilized drivers) varies depending on the testing objectives. To address this issue, we propose the On-demand Scenario Generation (OSG) Framework, …

Ef21 With Bells & Whistles: Six Algorithmic Extensions Of Modern Error Feedback, Ilyas Fatkhullin, Igor Sokolov, Eduard Gorbunov, Zhize Li, Peter Richtarik

Research Collection School Of Computing and Information Systems

First proposed by Seide (2014) as a heuristic, error feedback (EF) is a very popular mechanism for enforcing convergence of distributed gradient-based optimization methods enhanced with communication compression strategies based on the application of contractive compression operators. However, existing theory of EF relies on very strong assumptions (e.g., bounded gradients), and provides pessimistic convergence rates (e.g., while the best known rate for EF in the smooth nonconvex regime, and when full gradients are compressed, is O(1/T2/3), the rate of gradient descent in the same regime is O(1/T)). Recently, Richtàrik et al. (2021) proposed a new error feedback mechanism, EF21, based …

Predicting Consumers’ Purchase Intention Of Browsed Products: A Study Based On Eye‑Tracking, Feiyan Jia, Choon Ling Sia, Yani Shi, Fiona Fui-Hoon Nah, Keng Siau

Research Collection School Of Computing and Information Systems

Predicting consumers’ purchase intention of browsed products enables sellers to implement nuanced promotion strategies to stimulate purchase. But how can we predict consumers’ purchase intention of browsed products? Our research demonstrates that consumers’ eye movement data collected when they browse products can serve this aim. We train and test the prediction model using logistic regression and random forest algorithms. Using data collected in a laboratory experiment, our empirical results show that both algorithms perform much better than a random guess, and the logistic regression performs slightly better than the random forest. Our findings imply that eye movement data enable sellers …

Verify All Traffic: Towards Zero-Trust In-Network Intrusion Detection Against Multipath Routing, Ziming Zhao, Zhaoxuan Li, Xiaofei Xie, Zhipeng Liu, Tingting Li, Jiongchi Yu, Fan Zhang, Binbin Chen

Research Collection School Of Computing and Information Systems

With the popularity of encryption protocols, machine learning (ML)-based traffic analysis technologies have attracted widespread attention. To adapt to modern high-speed bandwidth, recent research is dedicated to advancing zero-trust intrusion detection by offloading feature extraction and model inference into the network dataplane. Especially, with the rise of programmable switches, achieving line-speed ML inference becomes promising. However, existing research only considers a single switch node as a relay to conduct evaluation. This is far from real-world deployments involving multiple switches (given that zero-trust security assumes that threats can originate from anywhere, including within the network), particularly the multipath routing phenomenon that …

Alibaba: Building Advanced Intellectual Property Governance For E-Commerce Marketplaces, Liang Chen, Sin Mei Cheah, Can Huang, Guoqiao Liu

Asian Management Insights

How the global e-commerce powerhouse harnessed artificial intelligence (AI) to balance innovation and intellectual property (IP) rights protection.

University Leadership, Singapore Management University

Asian Management Insights

The future belongs to institutions that advance impact and prepare minds for lifelong learning. An interview with Dr Andrew Hamilton, President Emeritus of New York University and former Vice-Chancellor of Oxford University.

Cutting Through The Infodemic Efficiently: News Claims Surveillance And Llm-Based Lightweight Fact Verification, Xuan Zhang

Dissertations and Theses Collection (Open Access)

In the context of the current infodemic, the rapid spread of misinformation poses a severe threat to social stability and public health. Recently, the rise of deep learning technologies has offered the potential for accelerating the development of automated misinformation detection and verification. However, current technological capabilities and computational resources often prove inadequate for the exhaustive scrutiny required, rendering the enhancement of processing efficiency a critical imperative. Given the vast amount of data on the internet, current technology and computational power often fall short in timely and accurate scrutiny of each piece of information, making the improvement of processing efficiency …

Rich Models And Methods For On-Demand Same Day Deliveries, Zhiqin Zhang

Dissertations and Theses Collection (Open Access)

Same-day delivery has brought numerous conveniences to people’s lives, but it has also presented challenges in terms of service management. To effectively optimize on-demand same-day delivery operations within urban logistics, intelligent decision-making strategies capable of adapting to rapidly changing circumstances are essential. Employing effective decisionmaking strategies that account for order allocation, route planning, courier scheduling, and other relevant factors, is pivotal in advancing logistics operations, enhancing efficiency, customer satisfaction, and resource utilization in the context of dynamic same-day delivery problems.

The focus of this thesis revolves around different emerging challenges presented by on-demand same-day delivery problems, with a particular emphasis …

Interactive Generative Modeling: A Pathway For Improved Simulation And Decision Making, Changyu Chen

Dissertations and Theses Collection (Open Access)

This dissertation presents Interactive Generative Modeling (IGM), a unified perspective that integrates interactive paradigm and generative modeling to advance the development of general-purpose intelligent systems. IGM is motivated by the observation that while reinforcement learning (RL) has mastered a wide range of complex simulated tasks, it struggles to generalize in high-dimensional, open-ended tasks. In contrast, generative models excel in such settings due to their expressivity and their ability to serve as powerful priors (e.g., LLMs pretrained on massive corpora). By bridging these two paradigms, IGM offers a promising path forward.

The first direction explored in this dissertation is IGM for …

Resilience In Stem: How Gender-Professional Identity Integration (G-Pii) And Self-Compassion Empower Women To Thrive, Isabelle Chiew

Dissertations and Theses Collection (Open Access)

Fostering resilience is crucial for the retention of women in male-dominated fields such as STEM. This paper investigates the interplay between gender-professional identity integration (G-PII), resilience, and self-compassion through two complementary studies. It is hypothesised that G-PII positively predicts resilience, with higher levels of integration associated with greater resilience. Furthermore, self-compassion is expected to moderate this relationship. Study 1 employs a cross sectional survey design to explore the relationships between G-PII, self-compassion, and resilience, while Study 2 uses an experimental design to assess the causal impact of G-PII on resilience. Study 1 found that G-PII was significantly and positively associated …

Learning And Optimization Under Human-Centric Considerations, Qian Shao

Dissertations and Theses Collection (Open Access)

This dissertation investigates learning and optimization problems shaped by humancentric considerations, such as preferences, demonstrations, behavioral patterns, and resource constraints. As real-world decision-making increasingly involves interaction with human agents, data, and limitations, modeling these factors becomes critical for building practical, adaptive, and robust systems.

The research spans four domains. First, we study preference-aware delivery routing by learning implicit practitioner preferences and incorporating them into a hierarchical route optimization framework. Second, we develop imitation learning methods for cost-constrained settings, enabling agents to mimic expert behavior while respecting safety and resource limitations. Third,we explore early rumor detection in data-limited environments, integrating large …

Irhunter: Universal Detection Of Instruction Reordering Vulnerabilities For Enhanced Concurrency In Distributed And Parallel Systems, Guohua Xin, Guangquan Xu, Yao Zhang, Cheng Wen, Cen Zhang, Xiaofei Xie, Neal N. Xiong, Shaoying Liu, Pan Gao

Research Collection School Of Computing and Information Systems

Instruction reordering is an essential optimization technique used in both compilers and multi-core processors to enhance parallelism and resource utilization. Although the original intent of this technique is to benefit the program, some improper reordering can significantly impact the program correctness, which we call instruction reordering vulnerability (IRV). However, existing methods detect IRV by defining CPU instruction reordering rules to schedule execution paths while neglecting compiler reordering, and thus generate false positives that require manual filtering and resulting in inefficiency. To bridge this gap, in this paper, we propose the IRV detection method, , which analyzes IRV characteristics and extracts …

Contested: Consistency-Aided Tested Code Generation With Llm, Jinhao Dong, Jun Sun, Wenjie Zhang, Jinsong Dong, Dan Hao

Research Collection School Of Computing and Information Systems

Recent advancements in large language models (LLMs) have significantly improved code generation, which generates code snippets automatically based on natural language requirements. Despite achieving state-of-the-art performance, LLMs often struggle to generate accurate and reliable code, requiring developers to spend substantial effort debugging and evaluating the generated output. Researchers have proposed leveraging Consistency to select code that passes more tests (inter-consistency) and demonstrates consistent behavior across more counterparts (intra-consistency). However, since the tests themselves are also generated by LLMs, relying on majority voting based on incorrect tests leads to unreliable results. To address this, we propose a lightweight interaction framework that …

Enhancing Vulnerability Detection Via Inter-Procedural Semantic Completion, Bozhi Wu, Chengjie Liu, Zhiming Li, Yushi Cao, Jun Sun, Shang-Wei Lin

Research Collection School Of Computing and Information Systems

Inspired by advances in deep learning, numerous learning-based approaches for vulnerability detection have emerged, primarily operating at the function level for scalability. However, this design choice has a critical limitation: many vulnerabilities span multiple functions, causing function-level approaches to lose the semantics of called functions and fail to capture true vulnerability patterns. To address this issue, we propose VulnSC, a novel framework designed to enhance learning-based approaches by complementing inter-procedural semantics. VulnSC retrieves the source code of called functions for datasets and leverages large language models (LLMs) with well-designed prompts to generate summaries for these functions. The datasets, enhanced with …

Lessons Learned From Sandboxing, Piloting And Policy Experimentation With Ai And Other Digital Initiatives: Part 1, Summary Report, Steven M. Miller

Research Collection School Of Computing and Information Systems

This report, "Lessons Learned from Sandboxing, Piloting and Policy Experimentation with AI and Other Digital Initiatives," captures insights and experiences from project experts involved in recent digital innovation initiatives with the governments of Bangladesh, Maldives, and Kazakhstan, and from project experts actively involved with the use of AI for delivering government digital services in the EU, New Zealand, Rwanda, Singapore, United States, and Uzbekistan. The ten in-depth interview write-ups produced from these nine different country settings provide a small but highly informative sample of rich descriptions of some of the important realities, approaches, nuances, issues and challenges related to testing …