Digital Commons Network^™

Open Research For Robustifying Data-Centric Systems, Manuel Rigger, Jinsheng Ba, Wenjing Deng, Rajdeep Singh Hundal, Nathee Jaywaree, Yuancheng Jiang, Yuxi Ling, Shuxin Li, Qiuyang Mang, Jovyn Tan, Ming Wei Tan, Chi Zhang, Tongjun Zhang, Suyang Zhong

Singapore Open Research Conference 2024

Lightning talk “Open Research for Robustifying Data-Centric Systems” by Winner of the Singapore Open Research Awards 2024, Assistant Professor Manuel RIGGER from National University of Singapore. Abstract: The NUS TEST lab has actively promoted and conducted open research in programming languages and software engineering. We provide publicly available artifacts for all our research projects, chair or participate in artifact-evaluation processes, and actively engage with companies and researchers based on our open-source tools. One focus area is increasing the reliability of data-centric systems. We have developed impactful tools such as SQLancer, in which we have realised multiple novel approaches, which allowed …

Optimizing Open Research: Data And Code Sharing At S-Lab, Chen Change Loy, Geong Sen Poh, Chee Guan Koh, Moi Moi Siew, Jin Boon Ng

Singapore Open Research Conference 2024

Lightning talk “Optimizing Open Research - Data and Code Sharing at S-Lab” by Winner of the Singapore Open Research Awards 2024, Professor Chen Change LOY from Nanyang Technological University.

S-Lab for Advanced Intelligence (S-Lab) is committed to advancing transparency, reproducibility, and collaboration within the scientific community. By sharing data, demos, and codes on publicly discoverable platforms such as DR-NTU (Data), OpenMMLab, OpenXLab, GitHub, and Hugging Face, we make our codes and datasets open and reusable. We believe that by making open data and code FAIR - Findable, Accessible, Interoperable, and Reusable, they can be scrutinised, and reused by fellow researchers …

Pre-Mortem: Unf.A.I.R - The Death Of Open Research, Min-Yen Kan

Singapore Open Research Conference 2024

Despite the calls for more open research by their proponents, adoption towards Open Research lags. Looking through the lens of a pre-mortem, we'll deconstruct the failure of a hypothetical open research project (in part in terms of F.A.I.R.-ness: Findable, Accessible, Interoperable and Reusable) and take away how to design open research for better success.

Elevating Automated Software Maintenance Tasks With Large Language Models, Xin Zhou

Dissertations and Theses Collection (Open Access)

Software engineering involves many tasks across different phases such as requirements, design, implementation, testing, and maintenance. Among them, software maintenance is a crucial phase, typically accounting for more than half of the software life cycle's duration.
To boost developer productivity, in recent years, numerous research endeavors in software engineering have sought to automate certain software maintenance tasks through the application of machine learning techniques.
Since 2020, the emergence of advanced Large Language Models (LLMs) of code has opened new avenues for enhancing automated solutions in software maintenance.
This dissertation presents a series of works aimed at advancing automated solutions for …

Celebrating Professor Rita Mcgrath: Winner Of The Ck Prahalad Outstanding Scholar / Practitioner Award, Strategic Management Society, Us 2022: A Conversation With Howard Thomas, Rita Mcgrath, Howard Thomas

Research Collection Lee Kong Chian School Of Business

This article highlights Rita McGrath’s extraordinary career and contributions to management thinking, particularly at the intersection of strategy and innovation. Raised in a science-oriented family, McGrath’s academic journey began with a PhD at Wharton and continued at Columbia Business School. She pioneered concepts like “Discovery-Driven Planning” and the idea of “transient competitive advantage,” reshaping how organisations navigate uncertainty and innovation. Her works, including The End of Competitive Advantage and Seeing Around Corners, blend rigorous research with practical insights. A tireless advocate for diversity in academia, McGrath’s achievements bridge academic excellence and real-world impact, serving as an inspiration for future leaders.

Which Idea To Pursue? Gender Differences In Novelty Avoidance During Creative Idea Selection, Mengzi Jin, Roy Y. J. Chua

Research Collection Lee Kong Chian School Of Business

Despite women having made significant progress in the modern workforce, gender gaps are still evident in creative work. In this paper, we propose that, although women and men are equally capable of generating creative ideas, gender differences emerge during the idea-selection stage. Specifically, compared with men, women engage in higher novelty avoidance during idea selection—the degree to which one selects an idea that is less novel than the most novel idea one has generated. In two laboratory studies and a field survey involving creative professionals, we found significant gender differences in novelty avoidance during idea selection and identified women’s concerns …

Dc-Instruct : An Effective Framework For Generative Multi-Intent Spoken Language Understanding, Bowen Xing, Lizi Liao, Minlie Huang

Research Collection School Of Computing and Information Systems

In the realm of multi-intent spoken language understanding, recent advancements have leveraged the potential of prompt learning frameworks. However, critical gaps exist in these frameworks: the lack of explicit modeling of dual-task dependencies and the oversight of task-specific semantic differences among utterances. To address these shortcomings, we propose DC-Instruct, a novel generative framework based on Dual-task Inter-dependent Instructions (DII) and Supervised Contrastive Instructions (SCI). Specifically, DII guides large language models (LLMs) to generate labels for one task based on the other task’s labels, thereby explicitly capturing dual-task inter-dependencies. Moreover, SCI leverages utterance semantics differences by guiding LLMs to determine whether …

Why Isn’T Formula 1 Going Electric?, Terry Van Gevelt

Asian Management Insights

Electric vehicles are not the only sustainable automotive option.

1. While electric vehicles (EVs) are marketed as ‘zero-emission’, their overall environmental impact and battery production all contribute to their lifecycle emissions. In fact, their widespread adoption needs significant infrastructural changes like installing new charging networks and upgrading power grids, which come with substantial environmental and financial costs.

2. Considering a diverse array of energy alternatives, including synthetic e-fuels, could offer Singapore a that is tailored to the specific needs and infrastructural realities of the country and region.

Pigs And The City, Sayd Randle

Asian Management Insights

Urban greening requires a re-look at sharing space with animals and nature.

1. There are several challenges when balancing urban development with ecological sustainability, as seen in Singapore’s struggles with human-wildlife interactions like wild boars entering populated areas.

2. Opinions on managing wildlife diverge between calls for stricter population control and concerns over habitat loss. This shows the need for balanced approaches that cater to both humans and ecology alike.

3. Cities like Houston, Barcelona, and Hong Kong offer different models for human-wildlife management, showing that local contexts shape approaches to achieving peaceful coexistence with urban wildlife.

Urban H: Housing, Heat, And Health, Loretta Lees

Asian Management Insights

Future policy needs to triangulate the ‘triple-H’ to help marginalised urban populations.

1. The urban heat island effect generates disproportionately high temperatures in urban settlements compared to non-urban ones, leading to increased heat-related illnesses and mental health issues, especially among vulnerable and marginalised populations living in poorly-planned or -resourced areas.

The Urban-H research agenda by Boston University’s Initiative on Cities focuses on the interconnected effects of housing, heat, and health (triple-H) to develop a resilience index for cities.

3. The proposed global Urban-H Index could help cities worldwide address the triple-H crisis by guiding policymakers to craft equitable, as well …

Our Roads Are Choking Us, Mark Stevenson, Ferdinand Balfoort, Darius Balfoort

Asian Management Insights

Re-imagining transport systems to cut carbon emissions and drive climate change.

1. The global transport sector, particularly road transport, contributes significantly to global greenhouse gas (GHG) emissions and air pollution, causing serious health issues like respiratory and cardiovascular diseases, especially in highly urbanised areas.

2. In-vehicle telematics and smartphone apps that provide emission feedback can help incentivise drivers to adopt sustainable driving habits. A global carbon credit market can help achieve the same goal by letting individuals and companies monetise their emission reduction.

3. Transitioning to electric vehicles and micro- mobility solutions, with the support of proper infrastructure and regulations, …

Urban Sustainability: The Singapore Experience, Chuan Seng Lee

Asian Management Insights

The importance of green buildings, the circular economy, and zero waste.
Lee Chuan Seng, Chairman of the National Environment Agency (NEA) and founding President of the Singapore Green Building Council (SGBC), shares insights on urban sustainability. He emphasizes the significance of green buildings, the circular economy, and achieving zero waste. Lee also discusses strategies to promote the reduction and reuse of materials in the built environment, contributing to Singapore's leadership in sustainable urban development.

Power Shift: Steering The Energy Sector Towards A Net Zero Future, Tengku Muhammad Taufik

Asian Management Insights

Tengku Muhammad Taufik, President and Group CEO of PETRONAS, discusses how the global energy company navigates an increasingly volatile energy market while advancing its commitment to a Net Zero future. Balancing traditional operations with the demands of an accelerated energy transition, PETRONAS focuses on delivering energy to its stakeholders while meeting sustainability expectations. The company adopts frontier technologies and artificial intelligence (AI) as key enablers in its strategy to achieve a sustainable and resilient energy future.

Angels Or Demons: Investigating And Detecting Decentralized Financial Traps On Ethereum Smart Contracts, Jiachi Chen, Jiang Hu, Xin Xia, David Lo, John Grundy, Zhipeng Gao, Ting Chen

Research Collection School Of Computing and Information Systems

Decentralized Finance (DeFi) uses blockchain technologies to transform traditional financial activities into decentralized platforms that run without intermediaries and centralized institutions. Smart contracts are programs that run on the blockchain, and by utilizing smart contracts, developers can more easily develop DeFi applications. Some key features of smart contracts—self-executed and immutability—ensure the trustworthiness, transparency and efficiency of DeFi applications and have led to a fast-growing DeFi market. However, misbehaving developers can add traps or backdoor code snippets to a smart contract, which are hard for contract users to discover. We call these code snippets in a DeFi smart contract as “DeFi …

Revisiting The Conflict-Resolving Problem From A Semantic Perspective, Jinhao Dong, Jun Sun, Yun Lin, Yedi Zhang, Murong Ma, Jin Song Dong, Dan Hao

Research Collection School Of Computing and Information Systems

Collaborative software development significantly enhances development productivity by enabling multiple contributors to work concurrently on different branches. Despite these advantages, such collaboration often increases the likelihood of causing conflicts. Resolving these conflicts brings huge challenges, primarily due to the necessity of comprehending the differences between conflicting versions. Researchers have explored various automatic conflict resolution techniques, including unstructured, structured, and learning-based approaches. However, these techniques are mostly heuristic-based or black-box in nature, which means they do not attempt to solve the root cause of the conflicts, i.e., the existence of different program behaviors exhibited by the conflicting versions.In this work, we …

Ai And Creativity: Effects Of Culture And Task Emotiveness In Human-Ai Collaboration, Choon Ngee Tan

Dissertations and Theses Collection (Open Access)

Creativity is the driving force behind innovation, propelling individuals and societies toward progress by generating novel ideas and groundbreaking solutions. The emergence of generative AI models, exemplified by GPT-3, offers opportunities to enhance human creativity. This paper explores the potential for unprecedented breakthroughs through the synergy between human intuition and AI-driven creativity, providing practical guidance on leveraging AI to amplify creative capacities. Study 1 finds that AI models trained on data from the U.S. and Chinese cultures exhibit cultural norms, values and cognition of those cultures. Study 2 finds that when humans and AI models of the same culture collaborate …

Ai And Data Science For Public Policy, Kenneth Benoit

Research Collection School of Social Sciences

Artificial intelligence (AI) and data science are reshaping public policy by enabling more data-driven, predictive, and responsive governance, while at the same time producing profound changes in knowledge production and education in the social and policy sciences. These advancements come with ethical and epistemological challenges surrounding issues of bias, transparency, privacy, and accountability. This special issue explores the opportunities and risks of integrating AI into public policy, offering theoretical frameworks and empirical analyses to help policymakers navigate these complexities. The contributions explore how AI can enhance decision-making in areas such as healthcare, justice, and public services, while emphasising the need …

Law-Aware Autonomous Driving, Yang Sun

Dissertations and Theses Collection (Open Access)

Autonomous driving systems (ADSs) necessitate comprehensive testing prior to deployment in Autonomous Vehicles (AVs). High-fidelity simulators are crucial for this testing, as they can replicate a wide range of scenarios, including those that are difficult or dangerous to recreate in real-world conditions. While previous approaches have demonstrated that test cases can be generated automatically, they often focus on weak oracles (e.g., reaching the destination without collisions) and fail to assess whether the journey was conducted safely and in compliance with some complex property specifications such as traffic laws. In this dissertation, beyond assessing basic properties like energy consumption and proximity …

Towards Trustworthy Recommendation Systems: Beyond Collaborative Filtering, Zhongzhou Liu, Zhongzhou

Dissertations and Theses Collection (Open Access)

Recommendation systems have been widely deployed in various scenarios and applications, such as e-commerce, social media, and streaming services. Recommendation systems have significantly influenced how we interact with various items in a wide range of platforms. They help users discover their preferred items and provide efficient and enjoyable experiences. They also help item providers and platforms to quickly find their potential customers, thus increasing the total revenue and user engagement.

The majority of existing recommendation systems merely focus on the matching between users and items, aiming for higher recommendation accuracy. Collaborative filtering is regarded as one of the most successful …

Contactless And Scalable Approaches For Human Health And Performance Sensing, Ngoc Doan Thu Tran

Dissertations and Theses Collection (Open Access)

Human health and performance sensing has been extensively studied, from physiology to mental health and movement analytics. However, typical approaches rely on invasive and contact sensors or require professional practitioners, limiting their scalability. For example, the gold standard for measuring heart rate is through an electrocardiogram (ECG), which requires multiple probes attached to the skin and is impractical for individuals with skin issues. Additionally, it typically needs to be performed in a hospital setting under the supervision of a trained cardiac physiologist. Depression detection often relies on the expertise of psychologists or psychiatrists. However, there is a shortage of these …

Mitigating Operational Greenhouse Gas Emissions In Ageing Residential Buildings Using An Urban Digital Twin Dashboard, Pradeep Alva, Martín Mosteiro-Romero, Clayton Miller, Rudi Stouffs

Research Collection College of Integrative Studies

With the increasing stock of ageing infrastructure and resource constraints in Singapore, related risks and carbon emissions can be mitigated through long-term resilience planning, automated building inspection, and effective maintenance. Sustainable actions are needed to maintain Singapore's ageing infrastructure. Hence, a state-of-the-art control and management system is required in the form of smart city digital tools. We introduce an Urban Digital Twin (UDT)—GHG App for decision-makers in Singapore's operational building greenhouse gas (GHG) emission mitigation and decarbonisation initiatives. Based on multiple-criteria decision analysis (MCDA), a Potential for Intervention (PFI) map was created to rejuvenate the building system. Decision-makers can use …

A Dynamic Urban Digital Twin Integrating Longitudinal Thermal Imagery For Microclimate Studies, Vasantha Ramani, Marcel Ignatius, Joie Lim, Filip Biljecki, Clayton Miller

Research Collection College of Integrative Studies

Recently, the concept of a digital twin for the built environment has received significant attention due to its potential benefits to urban planners, engineers, and designers. The development of tools that aid in integrating real-world physical systems with digital capabilities is essential for advancing digital twin technology. In this work, we present one such digital twin tool that integrates the longitudinal thermal envelope data of buildings on the campus of the National University of Singapore with a virtual 3D model. Thermal images of the buildings were captured using a neighborhood-scale infrared observatory for a few months. The temperature profile of …

From Personal Comfort To District Performance: Using Smartwatch And Wifi Data For Occupant-Driven Operation, Martín Mosteiro-Romero, Matias Quintana, Clayton Miller, Rudi Stouffs

Research Collection College of Integrative Studies

This work proposes the use of a data-driven, agent-based model of building occupants’ activities and thermal comfort in an urban university campus in order to assess how district operation strategies can be leveraged to support the transition to flexible work arrangements. The results show that when users are given the flexibility to pursue more comfortable workspaces, they are still comfortable only 58% of the time.

Uncovering Merchants’ Willingness To Wait In On-Demand Food Delivery Markets, Jian Liang, Ya Zhao, Hai Wang, Zuopeng Xiao, Jintao Ke

Research Collection School Of Computing and Information Systems

While traditional on-demand food delivery services help restaurants reach more customers and enable doorstep deliveries, they also come with drawbacks, such as high commission fees and limited control over the delivery process. White-label food delivery services have emerged as an alternative, ready-to-use platform for restaurants to arrange delivery for customer orders received through their applications or websites, without the constraints imposed by traditional on-demand food delivery platforms or the need to develop an in-house delivery operation. Although several studies have investigated consumer behavior when using traditional on-demand food delivery services, there is limited research on merchants’ behavior when adopting white-label …

Badfl: Backdoor Attack Defense In Federated Learning From Local Model Perspective, Haiyan Zhang, Xinghua Li, Mengfan Xu, Ximeng Liu, Tong Wu, Jian Weng, Robert H. Deng

Research Collection School Of Computing and Information Systems

There is substantial attention to federated learning with its ability to train a powerful global model collaboratively while protecting data privacy. Despite its many advantages, federated learning is vulnerable to backdoor attacks, where an adversary injects malicious weights into the global model, making the global model's targeted predictions incorrect. Existing defenses based on identifying and eliminating malicious weights ignore the similarity variation of the local weights during iterations in the malicious model detection and the presence of benign weights in the malicious model during the malicious local weight elimination, resulting in a poor defense and a degradation of global model …

Don’T Just Say “I Don’T Know”! Self-Aligning Large Language Models For Responding To Unknown Questions With Explanations, Yang Deng, Yong Zhao, Moxin Li, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Despite the remarkable abilities of Large Language Models (LLMs) to answer questions, they often display a considerable level of overconfidence even when the question does not have a definitive answer. To avoid providing hallucinated answers to these unknown questions, existing studies typically investigate approaches to refusing to answer these questions. In this work, we propose a novel and scalable self-alignment method to utilize the LLM itself to enhance its response-ability to different types of unknown questions, being capable of not only refusing to answer but also providing explanation to the unanswerability of unknown questions. Specifically, the Self-Align method first employ …

A Survey Of Ontology Expansion For Conversational Understanding, Jinggui Liang, Yuxia Wu, Yuan Fang, Hao Fei, Lizi Liao

Research Collection School Of Computing and Information Systems

In the rapidly evolving field of conversational AI, Ontology Expansion (OnExp) is crucial for enhancing the adaptability and robustness of conversational agents. Traditional models rely on static, predefined ontologies, limiting their ability to handle new and unforeseen user needs. This survey paper provides a comprehensive review of the state-of-the-art techniques in OnExp for conversational understanding. It categorizes the existing literature into three main areas: (1) New Intent Discovery, (2) New Slot-Value Discovery, and (3) Joint OnExp. By examining the methodologies, benchmarks, and challenges associated with these areas, we highlight several emerging frontiers in OnExp to improve agent performance in real-world …

Navigating Weight Prediction With Diet Diary, Yinxuan Gui, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Current research in food analysis primarily concentrates on tasks such as food recognition, recipe retrieval and nutrition estimation from a single image. Nevertheless, there is a significant gap in exploring the impact of food intake on physiological indicators (e.g., weight) over time. This paper addresses this gap by introducing the DietDiary dataset, which encompasses daily dietary diaries and corresponding weight measurements of real users. Furthermore, we propose a novel task of weight prediction with a dietary diary that aims to leverage historical food intake and weight to predict future weights. To tackle this task, we propose a model-agnostic time series …

Irl For Restless Multi-Armed Bandits With Applications In Maternal And Child Health, Gauri Jain, Pradeep Varakantham, Haifeng Xu, Aparna Taneja, Prashant Doshi, Milind Tambe

Research Collection School Of Computing and Information Systems

Public health practitioners often have the goal of monitoring patients and maximizing patients’ time spent in “favorable” or healthy states while being constrained to using limited resources. Restless multi-armed bandits (RMAB) are an effective model to solve this problem as they are helpful to allocate limited resources among many agents under resource constraints, where patients behave differently depending on whether they are intervened on or not. However, RMABs assume the reward function is known. This is unrealistic in many public health settings because patients face unique challenges and it is impossible for a human to know who is most deserving …

Defending Large Language Models Against Jailbreak Attacks Via Layer-Specific Editing, Wei Zhao, Zhe Li, Yige Li, Jun Sun, Jun Sun

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are increasingly being adopted in a wide range of realworld applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts even when aligned via Reinforcement Learning from Human Feedback or supervised fine-tuning. While existing defense methods focus on either detecting harmful prompts or reducing the likelihood of harmful responses through various means, defending LLMs against jailbreak attacks based on the inner mechanisms of LLMs remains largely unexplored. In this work, we investigate how LLMs respond to harmful prompts and propose a novel defense method termed Layer-specific Editing (LED) …