Digital Commons Network^™

Lighttransfer: Your Long-Context Llm Is Secretly A Hybrid Model With Effortless Adaptation, Xuan Zhang, Fengzhuo Zhang, Cunxiao Du, Chao Du, Tianyu Pang, Wei Gao, Min Lin

Research Collection School Of Computing and Information Systems

Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hybrid models and the broad availability of pretrained large transformer backbones, we explore transitioning transformer models into hybrid architectures for a more efficient generation. In this work, we propose LightTransfer, a lightweight method that transforms models such as LLaMA into hybrid variants. Our approach identifies lazy layers -- those focusing on recent or initial tokens -- and replaces their full attention with streaming attention. This transformation can be performed without any training for long-context …

Foreword, Pey Woan Lee

Singapore Law Journal (Lexicon)

No abstract provided.

Acknowledgements, Ee Ing Ong

Singapore Law Journal (Lexicon)

No abstract provided.

The Law On Deposits In Singapore, Tiong Min Yeo

Singapore Law Journal (Lexicon)

This article traces the development of the law of deposits in Singapore and reviews the restatement of the law in the 2024 landmark decision of the Court of Appeal in Li Jialin v Wingcrown Investments Pte Ltd, as well as some of the issues left open by the decision. It is argued that while the decision has clarified that deposits are not subject to the penalty rule but instead subject to the common law test of reasonableness—with the practical consequence that, with clear drafting, contracting parties can rely on the validity of reasonable deposit clauses without the complication of …

A Settlement By “Any Other Name”: Evaluating The Sustainability Of Settlement Mechanisms, Dorcas Quek Anderson

Singapore Law Journal (Lexicon)

Private settlements have been consistently encouraged by the Singapore civil justice system. Depending on the context, the settlement may take on many forms, including consent orders and settlement agreements. This begs the question of whether the exact form of settlement matters, or whether a settlement “by any other name” suffices. This article proposes the concept of “sustainable settlements” – comprising the measures of ease of enforcement, finality, and confidentiality – to holistically appraise the effectiveness of settlement mechanisms. The assessment of six settlement mechanisms using these measures clearly indicates that not every mechanism is equally sustainable. Exploring settlement amidst the …

Where Singapore Meets Asean: Shaping Insolvency Reform For Micro And Small Enterprises, Lovein Leying Sui

Singapore Law Journal (Lexicon)

Given the economic dependence on micro and small enterprises (MSEs) in the ASEAN region, the MSE insolvency regime is of paramount regional importance. Evidence indicates that the ASEAN region has prioritised the improvement of such a regime, especially after the financial instability following the COVID-19 pandemic. This paper explores how trends in ASEAN MSE insolvency can inform Singapore’s insolvency reforms to improve MSE access and efficiency, while also considering broader implications for the region.

The Guilty Plea Discount: An Elaboration On Singapore’S Guidelines, Genieve Zhi Yi Wu

Singapore Law Journal (Lexicon)

Over the past two decades, a defining feature of Singapore’s sentencing regime has been the creation of structured sentencing methodology, with the aim of ensuring broad consistency and fairness across offenders. The exercise of judicial discretion in sentencing has largely been guided by statutory frameworks and guideline judgments. However, beyond the legislature and judiciary, an inter-agency body named the Sentencing Advisory Panel has also been formed to issue persuasive but non-binding guidelines. This article focuses on the first set of guidelines issued by the Sentencing Advisory Panel in 2023, concerning the sentencing of accused persons who plead guilty. It explains …

Revisiting Letters Of Credit And The Enforceability Of Sanctions Clauses: Case Comment: Kuvera Resources Pte Ltd V Jpmorgan Chase Bank, N.A., Bing Feng, Keith Law

Singapore Law Journal (Lexicon)

This article is a case commentary on the recent Singapore Court of Appeal decision of Kuvera Resources Pte Ltd v JPMorgan Chase Bank, N.A. [2023] 2 SLR 389. It begins with a brief review of the structure of documentary credit transactions before setting out the judgments by the High Court and Court of Appeal. The commentary then examines how both courts rationalised letters of credit within the traditional framework of unilateral contracts, before scrutinising the current position of sanctions clauses within letters of credit. It disagrees with the Court of Appeal’s hesitance towards accepting such clauses, noting that the unilateral …

1 Front Matter, Smu Lexicon

Singapore Law Journal (Lexicon)

Front matter with cover page, title page, title verso (copyright page) and table of contents.

Regulatory Impacts On Us Hazardous Waste Exports, Xiaofan Ji, Mengyu Wang, Tianyi Zhang

Sim Kee Boon Institute for Financial Economics

This paper examines the impact of key domestic and international regulations on US hazardous waste exports, focusing on shifts in export destinations and waste types from 2002 to 2023. Since 2005, OECD countries and US Trade Agreement Partners have become primary destinations for US hazardous waste, with significant surges after 2018 and a notable decline in 2022. An analysis of the regulatory landscape reveals that, while international frameworks such as the Basel Convention of 2021 have had a relatively limited impact on reducing US hazardous waste exports, domestic policies—particularly those in California—have more directly influenced export behaviors. Additionally, the US …

Learning Orientation Field For Osm-Guided Autonomous Navigation, Yuming Huang, Wei Gao, Zhiyuan Zhang, Maani Ghaffari, Dezhen Song, Cheng-Zhong Xu, Hui Kong

Research Collection School Of Computing and Information Systems

OpenStreetMap (OSM) has gained popularity recently in autonomous navigation due to its public accessibility, lower maintenance costs, and broader geographical coverage. However, existing methods often struggle with noisy OSM data and incomplete sensor observations, leading to inaccuracies in trajectory planning. These challenges are particularly evident in complex driving scenarios, such as at intersections or facing occlusions. To address these challenges, we propose a robust and explainable two-stage framework to learn an Orientation Field (OrField) for robot navigation by integrating LiDAR scans and OSM routes. In the first stage, we introduce a novel representation, OrField, which can provide orientations for each …

Preference-Based Deep Reinforcement Learning For Historical Route Estimation, Boshen Pan, Yaoxin Wu, Zhiguang Cao, Yaqing Hou, Guangyu Zou, Qiang Zhang

Research Collection School Of Computing and Information Systems

Recent Deep Reinforcement Learning (DRL) techniques have advanced solutions to Vehicle Routing Problems (VRPs). However, many of these methods focus exclusively on optimizing distance-oriented objectives (i.e., minimizing route length), often overlooking the implicit drivers' preferences for routes. These preferences, which are crucial in practice, are challenging to model using traditional DRL approaches. To address this gap, we propose a preference-based DRL method characterized by its reward design and optimization objective, which is specialized to learn historical route preferences. Our experiments demonstrate that the method aligns generated solutions more closely with human preferences. Moreover, it exhibits strong generalization performance across a …

The Imperial Gaze: Affective Governance, Hybrid Cartography, And China’S U-Shaped Line, William A. Callahan

Research Collection School of Social Sciences

This article develops ‘the imperial gaze’ concept to explore how maps not only represent the world, but also do things in geopolitics, even provoking mass demonstrations. It examines China’s early-modern and contemporary maps to highlight how they create an imperial gaze that guides Chinese understandings of world order. If your cartographic ‘view of the world’ produces your ideological ‘worldview’, then it is important to see how China’s early-modern maps inform the PRC’s twenty-first-century claims in the South China Sea. The article argues that Chinese cartography does things in geopolitics by mobilising the affective governance of an assemblage of hybrid combinations …

From Release To Adoption: Challenges In Reusing Pre-Trained Ai Models For Downstream Developers, Peerachai Banyongrakkul, Mansooreh Zahedi, Patanamon Thongtanunam, Christoph Treude, Haoyu Gao

Research Collection School Of Computing and Information Systems

Pre-trained models (PTMs) have gained widespread popularity and achieved remarkable success across various fields, driven by their groundbreaking performance and easy accessibility through hosting providers. However, the challenges faced by downstream developers in reusing PTMs in software systems are less explored. To bridge this knowledge gap, we qualitatively created and analyzed a dataset of 840 PTM-related issue reports from 31 OSS GitHub projects. We systematically developed a comprehensive taxonomy of PTM-related challenges that developers face in downstream projects. Our study identifies seven key categories of challenges that downstream developers face in reusing PTMs, such as model usage, model performance, and …

Merit Transference And The Paradox Of Merit Inflation, Matthew Hammerton

Research Collection School of Social Sciences

Many religious traditions and ethical systems hold that individuals accrue merit through their good intentions, acts, and character, and demerit through their bad intentions, acts, and character. This merit and demerit, accumulated by individuals throughout their lives, gives each person a kind of ethical “score” that can determine what they deserve, and influence whether good or bad things happen to them (e.g., divine punishments and rewards, a favourable or unfavourable rebirth, etc.). In some traditions (most notably Buddhism, but also to a limited extent in Hinduism, Islam, and Christianity), “merit transference” is a feature of these merit-based ethical systems. This …

Firm Digitalization And Accounting Jobs, Amanda Awyong, Qiang Cheng, Tian Deng, Rencheng Wang

Research Collection School Of Accountancy

This study examines how firm digitalization affects the demand for corporate accountants and their digital skills. Using more than 373,000 job posts for corporate accountants by U.S. non-technology firms between 2010 and 2019, we find that firm digitalization does not change the overall demand for financial specialists-accountants who are responsible for financial reporting, budgeting, and forecasting-but reduces the demand for financial clerks-accountants who primarily perform administrative financial tasks. We further show that firms digitalization increases the demand for digital skills among financial specialists, but not among financial clerks, and that such demand is greater than that for other employees within …

The New Framework For Directors’ Duty To Creditors And The Challenges Ahead – Foo Kian Beng V Op3 International Pte Ltd (In Liquidation) [2024] 1 Slr 361, Jonathan Ren Hao Cheong

Singapore Law Journal (Lexicon)

In Foo Kian Beng v OP3 International Pte Ltd (in liquidation) [2024] 1 SLR 361, the Singapore Court of Appeal introduced a two-step, three-category framework for evaluating whether a director has breached his fiduciary duty to consider the interests of creditors. This decision not only affirms the traditional understanding of the duty in other common law jurisdictions but also provides directors with clearer guidance on managing the affairs of the company in times of financial distress. This article builds upon the discussion in Foo Kian Beng by evaluating the new framework established by the SGCA. It also identifies potential challenges …

Boosting Symbolic Execution For Vulnerability Detection, Haoxin Tu

Dissertations and Theses Collection (Open Access)

Software systems written by humans tend to be unreliable and insecure, hence, bugs or vulnerabilities in them are inevitable. Symbolic execution has shown considerable potential in detecting diverse types of software bugs and also vulnerabilities that have severe security implications. However, existing symbolic execution engines still suffer from at least three fundamental limitations in memory modeling, path exploration, and structured input generation, which significantly impede existing engines from efficiently and effectively detecting software bugs and vulnerabilities.

The objective of this dissertation is to boost existing symbolic execution engines by designing a new memory model, two new path exploration strategies, and …

Memory-Efficient Graph Processing On Gpus: Reducing Intermediate Data Structure Overhead, Chang Ye

Dissertations and Theses Collection (Open Access)

The increasing scale of real-world graphs in domains such as fraud detection, community detection, and biological analysis demands high-throughput, memory-efficient graph processing solutions. GPUs offer massive parallelism for accelerating such workloads, and numerous frameworks have been developed to leverage their computational power. These frameworks primarily focus on optimizing scheduling to better align graph processing with GPU architectures. It performs well for algorithms with low memory demands, such as BFS, SSSP, and PageRank. However, for algorithms that require substantial memory, such as label propagation, and subgraph counting, the limited memory capacity of GPUs often becomes a significant bottleneck.

This dissertation addresses …

Impact Of Aigc Application On E-Commerce: A Study In The Scenario Of Product Display And Recommendation, Ya Shen

Dissertations and Theses Collection (Open Access)

Artificial Intelligence Generated Content is widely expected to enhance efficiency and lower operation cost for e-commerce. This study aims to investigate on how AIGC technology would impact on the online shopping behavior and conversion rate, specifically in the scenario of product display and recommendations.

Experiment 1 is to evaluate which scenario would have better efficiency on e-commerce platforms when using AIGC. Using an A/B testing methodology, the effects of AIGC application were measured among key factors of six product display and recommendation scenario on Vipshop.com. Results show that AIGC application on model image has the greatest impact, increasing CTR by …

The Dual Impact Of Ict Use On Work Autonomy, Workload, Work Engagement, And Work-Family Conflict: Moderating Effects Of Perceived Organizational Support And Conscientiousness, Shenghui Han

Dissertations and Theses Collection (Open Access)

This study investigates the dual impact of information and communication technology (ICT) use intensity on employee outcomes in the workplace, with a particular focus on work autonomy, workload, work engagement, and work–family conflict (WFC). Drawing upon the job demands-resources (JD-R) model and conservation of resources (COR) theory, I propose a dual-pathway framework in which ICT use intensity acts as both a job resource and a job demand. The study also examines the moderating roles of perceived organizational support (POS) and conscientiousness.

Data were collected from 414 full-time employees across six companies in China through a three-wave survey with two-week intervals …

Supporting Satisfaction, Satisfying Support: Bidirectional Associations Of Social Support And Life Satisfaction, Jonathan Louis Jie Sheng Chia, Andree Hartanto, William Tov

Research Collection School of Social Sciences

Existing literature has explored the impact of social support (SS) on life satisfaction (LS). However, the reciprocal relationship—that is, the influence of LS on SS—remains understudied, despite extant theoretical support. In addressing this gap, the present study employed bivariate latent growth modeling to examine bidirectional associations between SS and LS trajectories among 8,449 middle-aged and older adults in Singapore, over seven waves spanning almost 6 years. Results provided evidence supporting the notion of bidirectional associations. Specifically, baseline SS positively predicted subsequent changes in LS, and baseline LS positively predicted subsequent changes in SS. Findings underscore the potential for interventions and …

The Return Of Chinese Emigrants: Legal Barriers And Local Practices, Jiaqi M. Liu

Research Collection School of Social Sciences

While China has observed an increasing influx of foreign nationals, a notable phenomenon involves Chinese emigrants opting for return migration to reestablish themselves in their country of origin. The process of emigrants returning to China, referred to as “return and resettlement” (huiguo dingju 回国定居) in official terminology, however, is not automatic. Emigrant returnees must fulfill a set of selective and documentary criteria, implying that only economically affluent and duly documented migrants are permitted to resettle in China. Through a comprehensive review of national policies and an analysis of local practices in a diaspora hometown, this chapter argues that the hukou …

Storage Location Optimization In Automated Storage And Retrieval Systems: A Deep Reinforcement Learning Approach, Lingjun Wang, Aldy Gunawan, Pieter Vansteenwegen

Research Collection School Of Computing and Information Systems

This study investigates the optimization of storage location in automated storage and retrieval systems (AS/RS). We introduce an optimization approach based on the Deep Q-Network (DQN) algorithm to enhance warehouse task efficiency and minimize stacker travel during storage and retrieval. To accelerate the algorithm training process, we integrate a prioritized experience replay mechanism. Furthermore, we decouple action selection from value estimation within the DQN framework to address the issue of value overestimation. The proposed model is evaluated against three heuristic methods. The experimental results demonstrate that our approach significantly outperforms these baselines.

An Efficient Security-Enhanced Accountable Access Control For Named Data Networking, Jianfei Sun, Yuxian Li, Xuehuan Yang, Guomin Yang, Robert H. Deng

Research Collection School Of Computing and Information Systems

Named Data Networking (NDN) is embraced as the crucial implementation of Information-Centric Networking (ICN), enhancing content distribution and caching efficiency through edge routers. However, existing NDN architectures face significant security and privacy challenges, including: (a) a lack of secure and efficient access control; (b) inadequate support for flexible and selective content management by content publishers; (c) insufficient implementation of accountability and privilege revocation mechanisms. To handle these challenges, we propose ESAS, the first-ever Efficient Security-enhanced Accountable Access Control Scheme for NDN. Specifically, our ESAS incorporates anonymous authentication using group signatures at network routers to prevent unauthorized access, employs key-aggregation-based access …

Educator Perceptions Of Devops Teaching Recommendations And Their Alignment With Common Challenges, Marcelo Romulo Fernandes, Pablo Paiva, Samuel Lucas De Moura Ferino, Roberta Coelho, Christoph Treude, Eduardo Aranha, Uirá Kulesza

Research Collection School Of Computing and Information Systems

DevOps education presents unique pedagogical challenges due to the diversity of tools, rapid technological change, and the multidisciplinary nature of the field. Although previous work has proposed recommendations to address these challenges, it is unclear how educators perceive these recommendations and whether they align with the challenges encountered in practice. In this paper, we present a quantitative and qualitative methods study involving 11 DevOps educators who interacted with Improve, a tool that presents a curated set of educational challenges and recommendations derived from previous literature. Educators indicated which recommendations they already use, which they intend to use, and which challenges …

Large Lithium-Ion Battery Model For Secure Shared E-Bike Battery In Smart Cities, Donghui Ding, Zhao Li, Linhao Luo, Ming Jin, Bin Zhu, Yichen Zhong, Junhao Hu, Peng Cai, Huiqi Hu

Research Collection School Of Computing and Information Systems

Electric bikes powered by lithium-ion batteries are increasingly used in smart cities to promote sustainable mobility and efficient delivery services. However, limited battery range and slow plug-in charging remain key challenges. Shared electric bike battery systems, facilitated by battery swapping stations, offer a promising solution by enabling quick and efficient battery replacements. However, their success hinges on accurate anomaly detection, battery health estimation and remain range prediction. These tasks remain challenging due to data scarcity, battery diversity and environmental variability. Here we show that a large-scale lithium-ion battery model trained on over ten million battery time series data enables robust …

Stylegan-∞: Extending Stylegan To Arbitrary-Ratio Translation With Stylebook, Yihua Dai, Tianyi Xiang, Bailin Deng, Yong Du, Hongmin Cai, Jing Qin, Shengfeng He

Research Collection School Of Computing and Information Systems

Although pre-trained large-scale generative models StyleGAN series have proven to be effective in various editing and translation tasks, they are limited to pre-defined fixed aspect ratio. To overcome this limitation, we propose StyleGAN-∞, a model that enables pre-trained StyleGAN to perform arbitrary-ratio conditional synthesis. Our key insight is to distill the expressive StyleGAN features into a StyleBook, such that an arbitrary-ratio condition can be translated to other forms by properly assembling pre-defined StyleBook vectors. To learn and leverage the StyleBook, we employ a network with three distinct stages, each corresponding to StyleBook extraction, StyleBook correspondence learning, and arbitrary-ratio synthesis. Extensive …

Stable And Fair Cost Allocation In Platform-Enabled Lcl Consolidation, Pang Jin Tan, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

Many logistics platforms enable collaboration between agents to reduce costs, but determining fair pricing remains challenging when agents have pre-existing partnerships. This paper introduces a cooperative game theory framework to model platform-mediated collaboration, modeling the platform as an additional player. We present a novel characteristic function that distinguishes between partial collaborations (existing relationships) and full collaborations (platform-enabled). Using Shapley value, we derive fair cost allocations and platform charges that reflect each participant's contribution. We address stability concerns through an optimization model that minimizes platform subsidies while preventing profitable deviations. The framework is demonstrated through an application in freight forwarding for …

Dgl: Dynamic Global-Local Information Aggregation For Scalable Vrp Generalization With Self-Improvement Learning, Yubin Xiao, Yuesong Wu, Rui Cao, Di Wang, Zhiguang Cao, Xuan Wu, Peng Zhao, Yuanshu Li, You Zhou, Yuan Jiang

Research Collection School Of Computing and Information Systems

The Vehicle Routing Problem (VRP) is a critical combinatorial optimization problem with wide-reaching real-world applications, particularly in logistics, transportation. While neural network-based VRP solvers have shown impressive results on test instances similar to training data, their performance often degrades when faced with varying scales and unseen distributions, limiting their practical applicability. To overcome these limitations, we introduce DGL (Dynamic Global-Local Information Aggregation), a novel model that combines global and local information to effectively solve VRPs. DGL dynamically adjusts local node selections within a localized range, capturing local invariance across problems of different scales and distributions, thereby enhancing generalization. At the …