Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 91 - 120 of 15936

Full-Text Articles in Entire DC Network

Beyond Earnings Quality: Evaluating The Quality Of Corporate Disclosure Practices, Patricia M. Dechow, Weili Ge, Wei Ting Loh Jul 2026

Beyond Earnings Quality: Evaluating The Quality Of Corporate Disclosure Practices, Patricia M. Dechow, Weili Ge, Wei Ting Loh

Research Collection School Of Accountancy

We propose a framework to assess the decision-usefulness of heterogeneous disclosure practices that managers use to convey information to market participants. We illustrate an application of our framework to non-GAAP earnings, management earnings guidance, and earnings conference calls. We first identify key quality attributes for each disclosure practice and then develop a list of quality metrics that we apply to a small pilot sample. We focus on metrics that are easily measured in real time and discuss the practical challenges of conducting assessments of disclosure quality at the firm-quarter-disclosure level. Our descriptive analysis provides preliminary insights into whether and how …

Go to article

Generation-Augmented Video Corpus Moment Retrieval, Mingjin Kuai, Qianyin Xiao, Juncheng Li, Jin Peng, Lizi Liao, Wei Ji Jul 2026

Generation-Augmented Video Corpus Moment Retrieval, Mingjin Kuai, Qianyin Xiao, Juncheng Li, Jin Peng, Lizi Liao, Wei Ji

Research Collection School Of Computing and Information Systems

Video Corpus Moment Retrieval (VCMR) requires models to efficiently retrieve and precisely locate specific moments relevant to natural language queries within a massive, untrimmed video corpus. However, existing discriminative approaches typically rely on shallow visual-textual feature matching mechanisms, which often struggle to capture fine-grained semantic differences. To address this limitation, we propose Video-GAR, a novel framework that reframes the conventional retrieval task from superficial matching to generative understanding, positing that the capability for query reconstruction evidences deep semantic comprehension. Specifically, Video-GAR orchestrates three synergistic components: To overcome the computational efficiency bottleneck, we construct a Bi-Mamba backbone that leverages the linear …

Go to article

A Refined Generalization Analysis For Extreme Multi-Class Supervised Contrastive Representation Learning, Minh Hieu Nong, Antoine Ledent Jul 2026

A Refined Generalization Analysis For Extreme Multi-Class Supervised Contrastive Representation Learning, Minh Hieu Nong, Antoine Ledent

Research Collection School Of Computing and Information Systems

Contrastive Representation Learning (CRL) has achieved strong empirical success in multiple machine learning disciplines, yet its theoretical sample complexity remains poorly understood. Existing analyses usually assume that input tuples are identically and independently distributed, an assumption violated in most practical settings where contrastive tuples are constructed from a finite pool of labeled data, inducing dependencies among tuples. While one recent work analyzed this learning setting using U-Statistics to estimate the population risk, the techniques used therein require the risk of each class to concentrate uniformly, making excess risk bounds scale in the order of where denotes the probability of the …

Go to article

A Framework For Top-K Queries With Constrained Preferences, Kyriakos Mouratidis, Nikolaos Chaloulakos, Bo Tang Jul 2026

A Framework For Top-K Queries With Constrained Preferences, Kyriakos Mouratidis, Nikolaos Chaloulakos, Bo Tang

Research Collection School Of Computing and Information Systems

Traditional rank-aware processing assumes a dataset that contains available options to cover a specific need (e.g., restaurants, hotels, etc) and users who browse that dataset via top-k queries with linear scoring functions, i.e., by ranking the options according to the weighted sum of their attributes, for a set of given weights. In practice, however, user preferences (weights) may only be estimated with bounded accuracy, or may be inherently imprecise due to the inability of a human user to specify exact weight values with absolute accuracy. Motivated by this, we define the constrained-preference top-k (CT) query. Given an approximate description of …

Go to article

Knowledge-State Generative Agents For Pre-Assessment Question Evaluation, Ping Fan Ke, Yi Meng Lau, Siaw Ling Lo Jul 2026

Knowledge-State Generative Agents For Pre-Assessment Question Evaluation, Ping Fan Ke, Yi Meng Lau, Siaw Ling Lo

Research Collection School Of Computing and Information Systems

This paper introduces a Knowledge‑State Generative Agent framework for evaluating the quality of pre‑assessment questions. The framework employs large language model (LLM)–based agents prompted to adopt a teacher persona to simulate the responses of students with and without mastery of targeted knowledge components. A preliminary empirical study using archival data from 424 students enrolled in an Information Systems Management course indicates that the proposed approach yields interpretable metrics under Classical Test Theory. Results further show that agents instantiated with the relevant mastered knowledge components exhibit systematically higher performance than agents lacking such mastery. In addition, the study suggests that teacher-persona …

Go to article

Personal Goal Facilitation, Burnout And Work Engagement: The Role Of Self-Discrepancy, Jacinth Jia Xin Tan, Bek Wuay Tang Jul 2026

Personal Goal Facilitation, Burnout And Work Engagement: The Role Of Self-Discrepancy, Jacinth Jia Xin Tan, Bek Wuay Tang

Research Collection School of Social Sciences

Employees who perceive greater personal goal facilitation through work (PGFW) experience lower burnout and higher work engagement. This research examined whether self-discrepancies and emotional experiences explain these relationships across two cross-sectional studies involving a nationally representative sample of working adults (Study 1; N = 889) and a sample of public school teachers (Study 2; N = 228) in Singapore. Participants listed personal goals and rated how much their jobs facilitated these goals, alongside measures of self-discrepancy, emotions, burnout, and engagement. Across both samples, higher PGFW predicted lower burnout and greater engagement. These associations were consistently explained by lower ideal self-discrepancy …

Go to article

Sustainable Rural Development Under Ecological Civilization: Two Mountains Theory, “Green Rural Revival”, And Post-Productivist Transition In Zhejiang, Qian Forrest Zhang, Jianzhang Luo, Li Zhou Jul 2026

Sustainable Rural Development Under Ecological Civilization: Two Mountains Theory, “Green Rural Revival”, And Post-Productivist Transition In Zhejiang, Qian Forrest Zhang, Jianzhang Luo, Li Zhou

Research Collection School of Social Sciences

Existing studies of China’s overarching ideological framework for national development, “Ecological Civilization”, have focused narrowly on environmental governance; how it reshapes sustainable rural development remains underexplored. This paper pursues two analytically distinct tasks. First, it reconstructs the policy history of how President Xi Jinping’s “Two Mountains” theory was incorporated into the Eco-civilization framework and how Zhejiang Province’s “Green Rural Revival” (GRR) program, as a lived example of Eco-civilization, was elevated as the national template for rural development in 2024. Second, drawing on three cases from a sample of 21 villages in Zhejiang, it identifies three core practices of GRR and …

Go to article

Spatiotemporal Evolution And Influencing Factors Of The Coupling Coordination Between Agricultural Digitalization And Agricultural New Quality Productive Forces, Yuan Wang, Xiaoyuan Zhao, Chengxue Yang, Min Su Jul 2026

Spatiotemporal Evolution And Influencing Factors Of The Coupling Coordination Between Agricultural Digitalization And Agricultural New Quality Productive Forces, Yuan Wang, Xiaoyuan Zhao, Chengxue Yang, Min Su

Research Collection School of Social Sciences

The mutually reinforcing and coordinated development of Agricultural Digitalization (AD) and Agricultural New Quality Productive Forces (ANQPF) is an important path to achieving the modernization of agriculture and rural areas. Utilizing panel data from 31 provinces spanning 2012 to 2023, this study employs an Improved Coupling Coordination Degree Model (ICCDM), an Obstacle Degree Model (ODM), and a Random Effects Panel Tobit Model to investigate the spatiotemporal evolution patterns and the internal and external determinants of the Coupling Coordination Degree (CCD) between AD and ANQPF. The results indicate that: (1) From 2012 to 2023, both AD and ANQPF exhibited a steady …

Go to article

Occupation Ladders Over The Business Cycle, Ismail Baydur, Toshihiko Mukoyama Jul 2026

Occupation Ladders Over The Business Cycle, Ismail Baydur, Toshihiko Mukoyama

Research Collection School Of Economics

This paper studies occupational mobility over the business cycle. We divide occupations into two broad groups, “attractive” and “nonattractive”, where we label an occupation attractive if the total net inflow into this occupation through job-to-job transition is positive. We measure total net inflows into both occupation groups. We measure these inflows separately for job-to-job transitions and transitions from unemployment to employment. We find that the net inflow from nonattractive to attractive occupations through job-to-job transitions slows during recessions. The net inflow through transitions from unemployment has a similar cyclicality. This finding suggests a novel cost of recession: during recessions, workers …

Go to article

Through The Lens Of Clarity: Perceived Organizational Tightness Boosts Creativity For Men, But Not For Women, Grace J. H. Lim, Roy Y. J. Chua Jul 2026

Through The Lens Of Clarity: Perceived Organizational Tightness Boosts Creativity For Men, But Not For Women, Grace J. H. Lim, Roy Y. J. Chua

Research Collection Lee Kong Chian School Of Business

A commonly held perspective in the cultural tightness literature is that cultural tightness tends to negatively impact creativity. Yet some findings indicate that this relationship is not strictly negative and that a more nuanced perspective should be considered. Drawing on social information processing (SIP) theory and social role theory, we build theory on how the perception of organizational cultural tightness can increase creativity for some employees, but not for others. Specifically, we propose that perceived organizational tightness—the extent to which one perceives that an organization is characterized by strong norms and sanctions for deviation—increases clarity on creativity evaluation standards and …

Go to article

Global Prevalence Of Internet Gaming Disorder: An Umbrella Review Of Meta-Analytic Evidence And Implications For Child And Adolescent Psychiatry, Elisabeth C. S. Poon, Xun Ci Soh, Trina J. H. Poh, Andre C. S. Tan, Andree Hartanto Jul 2026

Global Prevalence Of Internet Gaming Disorder: An Umbrella Review Of Meta-Analytic Evidence And Implications For Child And Adolescent Psychiatry, Elisabeth C. S. Poon, Xun Ci Soh, Trina J. H. Poh, Andre C. S. Tan, Andree Hartanto

Research Collection School of Social Sciences

Background/Objectives: Internet gaming has become a widespread global activity, raising concerns about the prevalence of Internet Gaming Disorder (IGD). However, existing meta-analyses report highly variable prevalence estimates. This umbrella review aims to clarify the prevalence and variability of IGD by synthesizing evidence from meta-analyses to provide a comprehensive overview of IGD prevalence across populations, age groups, and regions. Methods: Following PRISMA guidelines, systematic searches were carried out across five published literature databases and two supplementary search sources. Title and abstract screening, followed by full-text eligibility assessment, were conducted independently by three authors. The same three authors then performed data extraction …

Go to article

Patent Regime Shift And Firm Innovation Strategy: Evidence From The Second Amendment To China's Patent Law, Tony W. Tong, Wenlong He, Liang Chen, Zi-Lin He, Jiangyong Lu Jul 2026

Patent Regime Shift And Firm Innovation Strategy: Evidence From The Second Amendment To China's Patent Law, Tony W. Tong, Wenlong He, Liang Chen, Zi-Lin He, Jiangyong Lu

Research Collection Lee Kong Chian School Of Business

Research Summary: While changes in intellectual property rights (IPR) protection significantly shape firm innovation, the mechanisms driving firms' responses remain poorly understood. Leveraging the Second Amendment to China's Patent Law, which strengthens appropriability particularly for state-owned enterprises (SOEs), as a natural experiment, we show that stronger IPR has mixed effects on SOEs' innovation. While SOEs increase the rate of innovation subsequent to the Amendment, they shift the direction of innovation toward more familiar areas in which they face a lesser need to adjust existing routines. This directional change suggests a quality decline in SOEs' innovation that may be attributed to …

Go to article

Keeping Up With The Times? Rethinking Social Evaluations Research Under Contemporary Technological And Sociopolitical Forces, Marco Clemente, Michael Etter, Yuliya Snihur, Gokhan Ertug, Graffin Scott, Anastasiya Zavyalova Jul 2026

Keeping Up With The Times? Rethinking Social Evaluations Research Under Contemporary Technological And Sociopolitical Forces, Marco Clemente, Michael Etter, Yuliya Snihur, Gokhan Ertug, Graffin Scott, Anastasiya Zavyalova

Research Collection Lee Kong Chian School Of Business

The context within which social evaluations form has been fundamentally altered by contemporary forces, such as digital technologies, polarization, activism, politicization of business, and geopolitical tensions. While research on social evaluations has generated rich insights into the formation and development of constructs, such as legitimacy, status, reputation, stigma, trust, and celebrity, much of this work has been developed under the assumptions of relative stability, coherent audiences, and well-defined intermediary roles. These assumptions are increasingly challenged in this changing context, requiring us to rethink the formation and management of social evaluations. The articles in this special issue focus on these changes. …

Go to article

Operational Agency: A Permeable Legal Fiction For Tracing Culpability In Ai Systems, Anirban Mukherjee, Hannah H. Chang Jul 2026

Operational Agency: A Permeable Legal Fiction For Tracing Culpability In Ai Systems, Anirban Mukherjee, Hannah H. Chang

Research Collection Lee Kong Chian School Of Business

Modern artificial intelligence (AI) systems act with a high degree of independence yet lack legal personhood—a paradox that fractures doctrines grounded in human-centric notions of mens rea and actus reus. This Article introduces Operational Agency (OA)—a permeable legal fiction structured as an ex post evidentiary framework—and Operational Agency Graph (OAG)—a tool for mapping causal interactions among human actors, organizations, and AI systems. OA evaluates an AI’s observable operational characteristics: its goal-directedness (as a proxy for intent), predictive processing (as a proxy for foresight), and safety architecture (as a proxy for standard of care). OAG operationalizes that analysis by embedding these …

Go to article

The Unintended Consequences Of International Student Shortage: Evidence From South Korea, Chung-Yoon Choi, Syngjoo Choi, Seonghoon Kim, Jongkwan Lee Jul 2026

The Unintended Consequences Of International Student Shortage: Evidence From South Korea, Chung-Yoon Choi, Syngjoo Choi, Seonghoon Kim, Jongkwan Lee

Research Collection School Of Economics

We study the role of international students in the higher education sector and the local economy by exploiting a policy reform in South Korea that restricted the admission of foreign students to local universities. By comparing the pre- and post-reform differences across universities with different pre-reform shares of international student enrollment, we show that an international student shortage resulting from this policy reform significantly worsened the financial outcomes of universities and consequently led to reduced investment in their students. We also document that a reduction in the number of international students in local areas decreased native employment, mainly in low-skilled …

Go to article

Navigating Unemployment Without Unemployment Insurance: Evidence From Singapore, Kim, Lanjie Wang Jul 2026

Navigating Unemployment Without Unemployment Insurance: Evidence From Singapore, Kim, Lanjie Wang

Research Collection School Of Economics

This study investigates the short-term impacts of unemployment among older workers (aged 50–62) in Singapore, a setting with-out public unemployment insurance. Using monthly panel data from the Singapore Life Panel, we analyse dynamic effects onmajor life outcomes such as income, spending, health, and subjective wellbeing over 2 years post-unemployment. Our findingsreveal substantial initial earnings losses with incomplete recovery: income remains 50.7% below pre-unemployment levels after24 months. Despite this persistent income gap, total household expenditure declines by 9.8% on average over 2 years (rangingfrom 7% to 16% across months). The implied two-year marginal propensity to consume is about 0.182, smaller than …

Go to article

Configuring Agentic Ai Coding Tools: An Exploratory Study, Matthias Galster, Seyedmoein Mohsenimofidi, Jai Lal Lulla, Muhammad Auwal Abubakar, Christoph Treude, Sebastian Baltes Jul 2026

Configuring Agentic Ai Coding Tools: An Exploratory Study, Matthias Galster, Seyedmoein Mohsenimofidi, Jai Lal Lulla, Muhammad Auwal Abubakar, Christoph Treude, Sebastian Baltes

Research Collection School Of Computing and Information Systems

Agentic AI coding tools increasingly automate software development tasks. Developers can configure these tools through versioned repository-level artifacts such as Markdown and JSON files. We present a systematic analysis of configuration mechanisms for agentic AI coding tools, covering Claude Code, GitHub Copilot, Cursor, Gemini, and Codex. We identify eight configuration mechanisms spanning from static context to executable and external integrations and, in an empirical study of 2,853 GitHub repositories, examine whether and how they are adopted, with a detailed analysis of Context Files, Skills, and Subagents. First, Context Files dominate the configuration landscape and are often the sole mechanism in …

Go to article

The Effect Of Vaccine Mandates On Disease Spread: Evidence From College Covid-19 Mandates, Riley K. Acton, Wenjia Cao, Emily E. Cook, Scott A. Imberman, Michael F. Lovenheim Jul 2026

The Effect Of Vaccine Mandates On Disease Spread: Evidence From College Covid-19 Mandates, Riley K. Acton, Wenjia Cao, Emily E. Cook, Scott A. Imberman, Michael F. Lovenheim

Research Collection School Of Economics

Nearly 700 4-year U.S. colleges mandated students receive COVID-19 vaccinations in fall 2021. Using data on college policies and county health, we estimate how mandates affect surrounding communities. Event studies from August to November 2021 show that mandates covering all colleges in a county reduced COVID-19 deaths by 5.6 per 100,000 persons, a 4.6% reduction in the U.S. total during this period. Mandates reduced COVID cases by 504 and ICU admissions by 16.2 per 100,000, though we see no statistically significant impact on hospitalizations. Impacts are larger in counties with larger college populations and low estimated ex-ante student vaccination rates.

Go to article

Integrated Optimization Of Farmland Cultivation And Fertilizer Application: Implications For Farm Management And Crop Production, Onur Boyabatli, Lusheng Shao, Yangfang (Helen) Zhou Jul 2026

Integrated Optimization Of Farmland Cultivation And Fertilizer Application: Implications For Farm Management And Crop Production, Onur Boyabatli, Lusheng Shao, Yangfang (Helen) Zhou

Research Collection Lee Kong Chian School Of Business

Motivated by the fresh produce industry, this paper studies a farmer’s joint cultivation and fertilizer (a representative farm input) application decisions facing uncertainties in yield, crop price, and harvesting cost where the latter two are yield dependent and yield is stochastically increasing in the fertilizer application rate. We develop a two-stage stochastic model of a farmer growing a commodity crop in a single season to maximize the expected profit. We then use the model to evaluate the optimal expected harvest volume (a measure of crop production). Our analytical analysis is complemented with numerical experiments calibrated to data. We characterize how …

Go to article

Robust Generator Maintenance Schedule For Frequency-Secure Power Systems, Yang Yang, Qiuzhuang Sun, Jimmy Chih-Hsien Peng, Loon Ching Tang, Zhisheng Ye Jul 2026

Robust Generator Maintenance Schedule For Frequency-Secure Power Systems, Yang Yang, Qiuzhuang Sun, Jimmy Chih-Hsien Peng, Loon Ching Tang, Zhisheng Ye

Research Collection College of Integrative Studies

Problem definition: Normal operations of a power system require that alternating current frequency be maintained at a nominal value, for example, 50 Hz, whereas severe deviation from this value due to power deficiencies can cause cascading generator trips. Maintaining the frequency requires adequate inertia and frequency regulation reserve, which are primarily provided by online generators. In daily operations, generators due for preventive maintenance must be taken offline, and thus an improper maintenance schedule could jeopardize frequency security, as exemplified by the recent Texas power blackout. However, this natural nexus between frequency security and maintenance has been over-looked largely in the …

Go to article

Online Planning Of Power Flows For Power Systems Against Bushfires Using Spatial Context, Jianyu Xu, Qiuzhuang Sun, Yang Yang, Huadong Mo, Daoyi Dong Jul 2026

Online Planning Of Power Flows For Power Systems Against Bushfires Using Spatial Context, Jianyu Xu, Qiuzhuang Sun, Yang Yang, Huadong Mo, Daoyi Dong

Research Collection College of Integrative Studies

A power station or transmission line can be affected due to bushfires, increasing operation costs. We study a fundamental but challenging problem of planning the optimal power flow (OPF) for power systems under bushfires. We develop a model to capture the stochastic nature of bushfire spread based on Moore’s neighborhood model and propose an online optimization modeling framework to sequentially plan power flows in the electricity network. Our framework assumes that bushfire spread is non-stationary over time and that the spread and containment probabilities are unknown. To address these challenges, we develop a contextual online learning algorithm that treats the …

Go to article

Learning By Writing: Exploring Authentic Legal Learning Through Case Summaries, Ee-Ing Ong, Wei Yang Quek, Duan Ning, Magdeleine Lew Jul 2026

Learning By Writing: Exploring Authentic Legal Learning Through Case Summaries, Ee-Ing Ong, Wei Yang Quek, Duan Ning, Magdeleine Lew

Research Collection Yong Pung How School Of Law

We use authentic learning as a pedagogical framework in a collaboration between our law school and the national Supreme Court of a Southeast Asian country, which facilitates law students’ development of their legal analytical and writing skills, and helps them better bridge the gap between existing legal curricula and the needs of legal practice. Akin to a writing apprenticeship, students write summaries on selected Supreme Court judgments, with their output reviewed by faculty as well as judicial law clerks from the court. The results are published on the court’s website and circulated to other stakeholders. In the post-exercise survey, participating …

Go to article

Offshore Philanthropy: A Critical Look At Family Offices Using Hybrid Trusts, Hang Wu Tang Jul 2026

Offshore Philanthropy: A Critical Look At Family Offices Using Hybrid Trusts, Hang Wu Tang

Research Collection Yong Pung How School Of Law

Family offices manage substantial wealth and often undertake philanthropic initiatives as part of their broader objectives. These offices may assume a variety of legal forms, ranging from corporations, partnerships, trusts administered by private trust companies or a combination of these forms. This article is concerned with family offices which use trusts administered by private trust companies in offshore jurisdictions. In response to competition for global wealth, several offshore jurisdictions have enacted trust laws that relax traditional doctrinal constraints to accommodate the needs of family offices. These include the creation of discretionary trusts for hybrid purposes in perpetuity ie trusts that …

Go to article

Multicbr: Multi‑View Contrastive Learning For Bundle Recommendation, Yunshan Ma, Yingzhi He, Xiang Wang, Yinwei Wei, Xiaoyu Du, Yuyangzi Fu, Tat‑Seng Chua Jul 2026

Multicbr: Multi‑View Contrastive Learning For Bundle Recommendation, Yunshan Ma, Yingzhi He, Xiang Wang, Yinwei Wei, Xiaoyu Du, Yuyangzi Fu, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Bundle recommendation seeks to recommend a bundle of related items to users to improve both userexperience and the profits of platform. Existing bundle recommendation models have progressed from capturing only user-bundle interactions to the modeling of multiple relations among users, bundles, and items.CrossCBR, in particular, incorporates cross-view contrastive learning into a two-view preference learningframework, significantly improving SOTA performance. It does, however, have two limitations: (1) the twoview formulation does not fully exploit all the heterogeneous relations among users, bundles, and items; and(2) the “early contrast and late fusion” framework is less effective in capturing user preference and difficultto generalize to …

Go to article

Late-Night And Early-Morning Train Scheduling With Non-Traffic Hour Maintenance Window In Urban Rail Transit Systems, Yaochen Ma, Hai Yang, Hai Wang Jul 2026

Late-Night And Early-Morning Train Scheduling With Non-Traffic Hour Maintenance Window In Urban Rail Transit Systems, Yaochen Ma, Hai Yang, Hai Wang

Research Collection School Of Computing and Information Systems

Regular maintenance during non-traffic hours (NTH) is vital for the resilience of urban rail transit (URT) systems, yet an insufficient NTH maintenance window poses a challenge for URT systems in various cities. For instance, the Hong Kong MTR Corporation has noted that the required NTH maintenance time often exceeds the available window, prompting service adjustments such as earlier late-night closures and/or later early-morning starts. To address this challenge, this study develops an optimal scheduling framework that links late-night and early-morning URT services through the NTH maintenance window requirement to maximize public welfare. A Decoupled Optimization Model (DOM) first derives closed-form …

Go to article

Survey On Learning-Based Dynamic Fault Localization: From Traditional Machine Learning To Large Language Models, Chunyan Liu, Yan Lei, Huan Xie, Jinping Wang, Yue Yu, David Lo Jul 2026

Survey On Learning-Based Dynamic Fault Localization: From Traditional Machine Learning To Large Language Models, Chunyan Liu, Yan Lei, Huan Xie, Jinping Wang, Yue Yu, David Lo

Research Collection School Of Computing and Information Systems

Learning-based dynamic fault localization techniques play a crucial role in the field of software engineering. These techniques dynamically execute test cases to meticulously extract useful knowledge from the execution information in the program, with the aim of identifying fault locations by leveraging machine learning, deep learning, and large language models. Currently, there is already a flourishing body of research that is intensely focused on learning-based dynamic fault localization. Research literature can be categorized into two main aspects for learning-based dynamic fault localization: data-based enhancements (i.e., the datasets) and model-based enhancements (i.e., the suspiciousness algorithms). Thus, we conduct an extensive literature …

Go to article

Deep Learning For Video Anomaly Detection: A Review, Peng Wu, Chengyu Pan, Yuting Yan, Guansong Pang, Qingsen Yan, Peng Wang, Yanning Zhang Jul 2026

Deep Learning For Video Anomaly Detection: A Review, Peng Wu, Chengyu Pan, Yuting Yan, Guansong Pang, Qingsen Yan, Peng Wang, Yanning Zhang

Research Collection School Of Computing and Information Systems

Video anomaly detection (VAD) aims to discover behaviors or events deviating from the normality in videos. As a long-standing task in the field of computer vision, VAD has witnessed much good progress. In the era of deep learning, with the explosion of architectures of continuously growing capability and capacity, a great variety of deep learning-based methods are constantly emerging for the VAD task, greatly improving the generalization ability of detection algorithms and broadening the application scenarios. Therefore, such a multitude of methods and a large body of literature make a comprehensive survey a pressing necessity. In this article, we present …

Go to article

Towards Uniformity And Alignment For Multimodal Representation Learning, Wenzhe Yin, Pan Zhou, Zehao Xiao, Jie Liu, Shujian Yu, Jan-Jakob Sonke, Efstratios Gavves Jul 2026

Towards Uniformity And Alignment For Multimodal Representation Learning, Wenzhe Yin, Pan Zhou, Zehao Xiao, Jie Liu, Shujian Yu, Jan-Jakob Sonke, Efstratios Gavves

Research Collection School Of Computing and Information Systems

Multimodal representation learning aims to construct a shared embedding space in which heterogeneous modalities are semantically aligned. Despite strong empirical results, InfoNCE-based objectives introduce inherent conflicts that yield distribution gaps across modalities. In this work, we identify two conflicts in the multimodal regime, both exacerbated as the number of modalities increases: (i) an alignment–uniformity conflict, whereby the repulsion of uniformity undermines pairwise alignment, and (ii) an intra-alignment conflict, where aligning multiple modalities induces competing alignment directions. To address these issues, we propose a principled decoupling of alignment and uniformity for multimodal representations, providing a conflict-free recipe for multimodal learning that …

Go to article

Rendering Data Unlearnable By Exploiting Llm Alignment Mechanisms, Ruihan Zhang, Jun Sun Jul 2026

Rendering Data Unlearnable By Exploiting Llm Alignment Mechanisms, Ruihan Zhang, Jun Sun

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are increasingly trained on massive, heterogeneous text corpora, raising serious concerns about the unauthorised use of proprietary or personal data during model training. In this work, we address the problem of data protection against unwanted model learning in a realistic blackbox setting. We propose Disclaimer Injection, a novel data-level defence that renders text unlearnable to LLMs. Rather than relying on model-side controls or explicit data removal, our approach exploits the models’ own alignment mechanisms: injecting carefully designed alignment-triggers to prevent effective learning. Through layer-wise analysis, we find that finetuning on such protected data induces persistent activation …

Go to article

Avadclip: Audio-Visual Collaboration For Robust Video Anomaly Detection, Peng Wu, Wanshun Su, Guansong Pang, Yujia Sun, Qingsen Yan, Peng Wang, Yanning Zhang Jul 2026

Avadclip: Audio-Visual Collaboration For Robust Video Anomaly Detection, Peng Wu, Wanshun Su, Guansong Pang, Yujia Sun, Qingsen Yan, Peng Wang, Yanning Zhang

Research Collection School Of Computing and Information Systems

With the increasing adoption of video anomaly detection in intelligent surveillance domains, conventional visual-only detection approaches often struggle with information insufficiency and high false-positive rates in complex environments. To address these limitations, we present a novel weakly supervised framework that leverages audio-visual collaboration for robust video anomaly detection. Capitalizing on the exceptional cross-modal representation learning capabilities of Contrastive Language-Image Pretraining (CLIP) across visual, audio, and textual domains, our framework introduces two major innovations: an efficient audio-visual fusion that enables adaptive cross-modal integration through lightweight parametric adaptation while maintaining the frozen CLIP backbone, and a novel audio-visual prompt that dynamically enhances …

Go to article

First Prev Next Last