Digital Commons Network^™

Llmqua: Practical Backdoor Injection On Large Language Model Quantization, Xiangxiang Chen, Peixin Zhang, Jun Sun, Jin Song Dong, Wenhai Wang, Jingyi Wang

Research Collection School Of Computing and Information Systems

Quantization is widely used to enable local deployment of large language models (LLMs) on resource-constrained devices. Recent work (e.g., QuRA) shows quantization can be exploited via rounding manipulation to implant backdoors. However, such an attack has been evaluated only on small models and does not directly apply to LLMs due to three key constraints: (1) limited poisoning data from small, task-agnostic calibration sets; (2) layer-wise quantization restricting adversarial access to global representations; and (3) lack of gradient access in quantization pipelines, blocking gradient-based attacks.We propose LLMQuA, a practical quantization-phase backdoor attack tailored to the LLM setting. LLMQuA (i) injects backdoors …

Prompting Frameworks For Large Language Models: A Survey, Xiaoxia Liu, Jingyi Wang, Jun Sun, Xiaohan Yuan, Guoliang Dong, Peng Di, Wenhai Wang, Dongxia Wang

Research Collection School Of Computing and Information Systems

Since the launch of ChatGPT, a powerful AI Chatbot developed by OpenAI, large language models (LLMs) have made significant advancements in both academia and industry, bringing about a fundamental engineering paradigm shift in many areas. While LLMs are powerful, it is also crucial to best use their power where “prompt” plays a core role. However, the booming LLMs themselves, including excellent APIs like ChatGPT, have several inherent limitations: (1) temporal lag of training data, and (2) the lack of physical capabilities to perform external actions. Recently, we have observed the trend of utilizing prompt-based tools to better utilize the power …

Teamwise: Exploring Virtually Embodied Ai Facilitation For Video-Based Team Onboarding, Venkata Akhila Rani Obilisetty, Mikkeline Elleby, Anthony Tang, April Yi Wang

Research Collection School Of Computing and Information Systems

AI-mediated facilitation has emerged as a scalable approach to supporting onboarding and coordination in newly formed remote teams, yet existing systems are predominantly text-based. To explore how video-based, virtually embodied AI facilitators shape team experiences, we present TeamWise, which joins video-based onboarding meetings as an on-screen avatar. TeamWise guides teams through a structured facilitation flow of low-stakes activities to foster rapport, mutual awareness, and shared identity. While the overall sequence of activities and facilitation goals is predefined, the facilitator’s turn-by-turn utterances are generated dynamically by an LLM in response to participant input. We conducted a formative study of TeamWise to …

Challenges In Synchronous And Remote Collaboration Around Visualization, Matthew Brehmer, Maxime Cordeil, Christophe Hurter, Takayuki Itoh, Wolfgang Büschel, Mahmood Jasim, Arnaud Prouzeau, David Saffo, Lyn Bartram, Sheelagh Carpendale, Chen Zhu-Tian, Andrew Cunningham, Anthony Tang, Samuel Huron, Masahiko Itoh, Arpit Joshi, Kiyoshi Kiyokawa, Hideaki Kuzuoka, Bongshin Lee, Guillermo Molina León

Research Collection School Of Computing and Information Systems

We characterize 16 challenges faced by those investigating and developing remote and synchronous collaborative experiences around visualization. Our work reflects the perspectives and prior research efforts of an international group of 29 experts from across human-computer interaction and visualization sub-communities. The challenges are anchored around five collaborative activities that exhibit a centrality of visualization and multimodal communication. These activities include exploratory data analysis, creative ideation, visualization-rich presentations, joint decision making grounded in data, and real-time data monitoring. The challenges also reflect the changing dynamics of these activities in the face of recent advances in extended reality (XR) and artificial intelligence …

Reasoning On Time-Series For Financial Technical Analysis, Kelvin J. L. Koa, Jan Chen, Yunshan Ma, Huanhuan Zheng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

While Large Language Models have been used to produce interpretable stock forecasts, they mainly focus on analyzing textual reports but not historical price data, also known as Technical Analysis. This task is challenging as it switches between domains: the stock price inputs and outputs lie in the time-series domain, while the reasoning step should be in natural language. In this work, we introduce Verbal Technical Analysis (VTA), a novel framework that combine verbal and latent reasoning to produce stock time-series forecasts that are both accurate and interpretable. To reason over time-series, we convert stock price data into textual annotations and …

Visual Loop: Bridging The Cognitive Gap In Software Development Through Visual-Ai Collaboration, Luis Filipe Fernandes Gomes, Xin Zhou, David Lo, Rui Abreu

Research Collection School Of Computing and Information Systems

Software development remains predominantly text-centric, despite decades of evidence showing that developers think and communicate visually. While sketches and diagrams externalize developers’ mental models, they remain disconnected from source code and quickly become outdated. Recent advances in foundation models, capable of both code and visual reasoning, create an opportunity to unify these representations. In this vision paper, we introduce Visual Loop, a continuous visual development environment that keeps code and informal sketches in bidirectional synchronization. Our prototype connects a code editor with a tablet-based visualization workspace, allowing developers to explore, annotate, and modify systems through freehand sketches interpreted by multimodal …

Autobackdoor: Automating Backdoor Attacks Via Llm Agents, Yige Li, Zhe Li, Wei Zhao, Nay Myat Min, Hanxun Huang, Xingjun Ma, Jun Sun

Research Collection School Of Computing and Information Systems

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted triggers and static data pipelines, which are rigid, labor-intensive, and inadequate for systematically evaluating modern defense robustness. As AI agents become increasingly capable, there is a growing need for more rigorous, diverse, and scalable \textit{red-teaming frameworks} that can realistically simulate backdoor threats and assess model resilience under adversarial conditions. In this work, we introduce \textsc{AutoBackdoor}, a general framework for automating backdoor injection, encompassing trigger generation, poisoned data …

Impending-Exit Period And Employee Performance: Rethinking Human Capital Disruption, Yea Hee Ko, Charlie O. Trevor

Research Collection Lee Kong Chian School Of Business

The well-established disruptive effects of employee turnover on firms have typically been attributed to post-exit dynamics, such as losses of human and social capital. Little is known, however, about leavers’ pre-exit job performance, which, if declining in sufficient magnitude as separation nears, may drive some of this disruption. Drawing on career concerns research, we argue that impending exit weakens incentives to improve future career prospects at the firm, thereby resulting in reduced performance. Our analysis reveals strikingly large negative relationships, as job performance during the impending-exit period declines by 53.9% and 79.8% across two performance measures. Additionally, we predict and …

Winner-Take-All In International Markets? Performance Persistence Of Social Platforms, Yang Yang, Liang Chen, Jiang Wei, Yang Liu

Research Collection Lee Kong Chian School Of Business

Strategy research has long linked sustained competitive advantage to barriers to imitation. We highlight network effects as an alternative mechanism and adopt a geotemporal perspective to theorize how firms sustain advantage as it unfolds over time in international markets. Our study examines this question through the performance persistence of social platforms, focusing on how institutional and demand-side conditions shape the sustainability of platforms’ competitive advantages. We propose that intellectual property rights protection may restrict the degree of freedom in information dissemination, dampening the role of network effects in sustaining superior performance, whilst demand heterogeneity may enhance the value of sizable …

Woulda, Shoulda, Coulda? The Impact Of Predictive, Prescriptive, And Prospective Expectations On Stakeholder Reactions, Yuri Mishina, Maxine Yu, David Gomulya

Research Collection Lee Kong Chian School Of Business

When and why might stakeholders react to firm activities in ways that might be different than, or even contradictory to, what we might expect based on the extant research? We draw on expectancy violation theory (EVT) and bring in the notion of heuristics and future-oriented expectations to examine this question, using a sample of investor reactions to earnings surprises from 2013 to 2019. We find that, in addition to comparing earnings to consensus earnings estimates, investors appear to compare the earnings surprises to the firm’s past performance and to its peers. Importantly, their expectations regarding future interactions with the firm …

Advancing The Understanding Of Palliative Care In Singapore: Knowledge, Attitudes, Receptiveness, And The Moderating Role Of Media Information-Seeking Preferences, Su Lin Yeo, Angel Lee, Raymond Han Lip Ng, May O. Lwin, Yumin Lin

Research Collection Lee Kong Chian School Of Business

Introduction: Despite the growing demand for palliative care, this specialized medical care remains severely underutilized, with almost 50% of countries worldwide lacking access. Given that misperceptions and stigma continue to hinder progress in healthcare policy, this study aims to examine the relationships between palliative care knowledge, attitudes, and receptiveness to better understand how public health communication can enhance awareness and understanding of the topic in Singapore. Applying the adapted knowledge-attitude-practice (KAP) model, it further extends theory by examining the moderating role of media information-seeking between knowledge and receptiveness.Methods: Mixed-mode surveys involving 1,226 participants (926 online and 300 in-person respondents), representing …

Price Discovery On Decentralized Exchanges, Agostino Capponi, Ruizhe Jia, Shihao Yu

Research Collection Lee Kong Chian School Of Business

Decentralized exchanges (DEXs) allow traders to express their willingness to pay for quick execution through a public priority fee bidding mechanism. We provide evidence that high-fee DEX trades are more informative and contribute more to price discovery. Using address-level blockchain transaction data, we show that informed traders persistently bid higher fees to secure early execution, revealing a strong willingness to pay for execution priority. Further, analysis of Ethereum mempool data demonstrates that informed traders employ a “jump bidding” strategy, placing high initial bids to deter potential competitors.

Financial Valuation Of Retirement Village Via Stochastic Modelling Of Disability Prevalence Rates, Jackie Li, Mingke Wang, Jia Liu, Jessica Wai Yin Leung

Research Collection School Of Economics

Global mortality rates continue to decline, and life expectancy continues its upward trend. Besides mortality levels, policymakers and providers of financial and health services would also be interested in disability prevalence and its potential future trajectories. The length of time in good health versus the duration with major disabilities or long-term illnesses has significant financial implications for both individuals and society. In this paper, we develop Bayesian common factor models to analyse Australian age- and sex-specific disability prevalence rates. In particular, there are one or more common factors shared by both sexes, as well as specific factors for each sex. …

High Dimensional Regression Coefficient Test With High Frequency Data, Dachuan Chen, Long Feng, Per A. Myklang, Lan Zhang

Research Collection School Of Economics

This paper presents the first study on high-dimensional regression coefficient tests with high-frequency financial data. These tests allow the number of regressors to be larger than the number of observations within each estimation block and can grow to infinity in asymptotics. In this paper, the sum-type test and max-type test have been proposed, where the former is suitable for the dense alternative (many small betas) and the latter is suitable for the sparse alternative (a very small number of large betas). By showing the asymptotic independence between the sum-type test and max-type test, the paper proposes a third test – …

Digital Storytelling For Institutional Memories: Lessons From Smuseum, Salihin Mohammed Ali

Research Collection Library

Agenda

• Setting the Context

• Case Study: SMUseum

• Governance & Collaboration

• Insights from Regional Practice

• Practical Takeaways

A Closer Look At The Innovator: The Interplay Between Divergent And Convergent Processes Of Self-Regulation, Ronald Bledow, Hye Jung Eun, Lien Vossaert

Research Collection Lee Kong Chian School Of Business

Creativity and innovation are essential for modern organizations. While abundant research has helped to better understand creativity in everyday work life, considerably less attention has been paid to how individuals achieve creative performance during the implementation of innovation projects. We articulate a dialectical interplay between divergent and convergent processes of self-regulation that supports creative performance in innovation projects. We propose that a divergent exploration orientation contributes to creative performance by inducing a broad search for novelty and by stimulating iteration—repeated cycles of experimentation and refinement. Convergent processes of self-regulation—outcome focus and planning—strengthen the relationship between divergent processes and creative performance. …

Institutional Cross-Ownership Of Peer Firms And Revelatory Price Efficiency, Young Jun Cho, Holly I. Yang, Yue Zhao

Research Collection School Of Accountancy

We argue that cross-ownership increases the amount of private information in stock price, enhancing the ability of stock price to provide feedback to managers. Consistent with this argument, we find greater cross-ownership heightens a firm’s investment-q sensitivity. This effect is stronger for firms with a lower propensity for voluntary disclosure and for firms whose managers hold less private information. Furthermore, we find that cross-ownership is negatively associated with the sensitivity of a firm’s investment to its peers’ stock prices. Additionally, cross-ownership has a stronger impact on the investment-q sensitivity when measured among investors who trade more actively the firm’s shares. …

Codeultrafeedback: An Llm-As-A-Judge Dataset For Aligning Large Language Models To Coding Preferences, Martin Weyssow, Aton Kamanda, Xin Zhou, Houari Sahraoui

Research Collection School Of Computing and Information Systems

Evaluating the alignment of large language models (LLMs) with user-defined coding preferences is a challenging endeavor that requires a deep assessment of LLMs' outputs. Existing methods and benchmarks rely primarily on automated metrics and static analysis tools, which often fail to capture the nuances of user instructions and LLM outputs. To address this gap, we introduce the LLM-as-a-Judge evaluation framework and present CodeUltraFeedback, a comprehensive dataset for assessing and improving LLM alignment with coding preferences. CodeUltraFeedback consists of 10,000 coding instructions, each annotated with four responses generated from a diverse pool of 14 LLMs. These responses are annotated using GPT-3.5 …

Plm-Effector: Unleashing The Potential Of Protein Language Models For Bacterial Secreted Protein Prediction, Dandan Zheng, Lihong Chen, Guansong Pang, Jian Yang

Research Collection School Of Computing and Information Systems

Bacterial secreted proteins, particularly effectors delivered by specialized secretion systems, are key mediators of virulence and host-pathogen interactions. However, accurate computational identification remains challenging, as many existing methods rely heavily on sequence similarity or handcrafted features, and often focus on a single secretion system. Recent studies have reported that some bacterial effectors may be associated with more than one secretion system, highlighting the complexity of secretion system annotation and motivating the development of system-aware computational prediction approaches. Here, we present PLM-Effector, a hybrid deep learning framework that integrates modern protein language models (PLMs) with multiple neural architectures via a two-layer …

Navigation Beyond Wayfinding: Robots Collaborating With Visually Impaired Users For Environmental Interactions, Shaojun Cai, Nuwan Janaka, Ashwin Ram, Janidu Shehan, Yingjia Wan, Kotaro Hara, David Hsu

Research Collection School Of Computing and Information Systems

Robotic guidance systems have shown promise in supporting blind and visually impaired (BVI) individuals with wayfinding and obstacle avoidance. However, most existing systems assume a clear path and do not support a critical aspect of navigation—environmental interactions that require manipulating objects to enable movement. These interactions are challenging for a human–robot pair because they demand (i) precise localization and manipulation of interaction targets (e.g., pressing elevator buttons) and (ii) dynamic coordination between the user’s and robot’s movements (e.g., pulling out a chair to sit). We present a collaborative human–robot approach that combines our robotic guide dog’s precise sensing and localization …

Private Set Intersection: A Systematic Review, Yunbo Yang, Defan Zhu, Jianting Ning, Qi Feng, Xiaoguo Li, Yuejia Cheng, Guomin Yang, Kui Ren

Research Collection School Of Computing and Information Systems

Various services, such as search engines, are increasingly deployed in cloud-based and distributed systems. However, data are typically managed by trusted servers, making user privacy and data security critical concerns. Private set intersection (PSI) is a powerful cryptographic primitive that enables multiple parties to compute the intersection of their datasets without revealing private inputs. It has been extensively studied over the past two decades, leading to significant gains in computational and communication efficiency. Yet, in many real-world scenarios, revealing the raw intersection may still leak sensitive information. To address this, numerous PSI variants have been developed to meet different application …

Improving Public Transport Through Machine Learning Influence Flow Analysis (Mifa): Southern England Bus Case Study, Benjamin Lee, Wolfgang Garn, Masoud Fakhimi, Nick F. Ryman-Tubb

Research Collection School Of Accountancy

Public transport (PT) is crucial for enhancing the quality of life and enabling sustainable urban development. As part of the UK Transport Investment Strategy, increasing PT usage is critical to achieving efficient and sustainable mobility. This paper introduces Machine Learning Influence Flow Analysis (MIFA), a novel framework for identifying the key influencers of PT usage. Using survey data from bus passengers in Southern England, we evaluate machine learning models. Subsequently, MIFA uncovers that easy payments, e-ticketing, and mobile applications can substantially improve the PT service. MIFA’s implementation demonstrates that strength and importance lead to specific insights into how service characteristics …

Identifying And Mitigating Api Misuse In Large Language Models, Terry Yue Zhuo, Junda He, Jiamou Sun, Zhenchang Xing, David Lo, John Grundy, Xiaoning Du

Research Collection School Of Computing and Information Systems

API misuse in code generated by large language models (LLMs) presents a serious and growing challenge in software development. While LLMs demonstrate impressive code generation capabilities, their interactions with complex library APIs are often error-prone, potentially leading to software failures and vulnerabilities. In this paper, we conduct a large-scale study of API misuse patterns in LLM-generated code, analyzing both method selection and parameter usage across Python and Java, using three representative LLMs (StarCoder-7B, Qwen2.5-Coder-7B, and GitHub Copilot). Based on extensive manual annotation of 3,209 method-level and 3,492 parameter-level misuses, we identify and categorize four recurring misuse types by building on …

Deep Learning Approaches For Anti-Money Laundering On Mobile Transactions: Review, Framework, And Directions, Jiani Fan, Lwin Khin Shar, Ruichen Zhang, Ziyao Liu, Wenzhuo Yang, Dusit Niyato, Kwok-Yan Lam

Research Collection School Of Computing and Information Systems

Money laundering is a financial crime that obscures the origin of illicit funds, necessitating the development and enforcement of anti-money laundering (AML) policies by governments and organizations. The proliferation of mobile payment platforms and smart IoT devices has significantly complicated AML investigations. As payment networks become more interconnected, there is an increasing need for efficient real-time detection to process large volumes of transaction data on heterogeneous payment systems by different operators such as digital currencies, cryptocurrencies, and account-based payments. Most of these mobile payment networks are supported by connected devices, many of which are considered loT devices in the FinTech …

Invert Your Prompt: Editing-Aware Diffusion Inversion, Yangyang Xu, Wenqi Shao, Yong Du, Haiming Zhu, Yang Zhou, Jiayuan Xie, Ping Luo, Shengfeng He

Research Collection School Of Computing and Information Systems

Recent advancements in text-guided diffusion models have enabled powerful image manipulation capabilities. However, balancing reconstruction fidelity and editability for real images remains a significant challenge. In this work, we introduce Editing Inversion (EditInv), a novel framework that inverts and edits real images for specific editing tasks by optimizing specific prompt embeddings within the extended  space. By leveraging distinct embeddings across different U-Net layers and time steps, EditInv seamlessly integrates inversion and editing through reciprocal optimization, ensuring both high fidelity and precise editability. This hierarchical editing mechanism classifies tasks into structure, appearance, and global edits, optimizing only those embeddings that are …

Cylindformer: Image-To-Point Cloud Registration With Cylindrical Transformer, Jingtao Wang, Hao Tang, Yanpeng Sun, Shengfeng He, Zechao Li

Research Collection School Of Computing and Information Systems

Accurate correspondence extraction between distinctive pixel-wise and point-wise features is critical for image-to-point cloud (I2P) registration. Recent efforts leveraging Transformers for I2P feature representation have demonstrated potential, primarily by first capturing intra-modality global contextual dependencies via self-attention, and then learning cross-modality correlations via cross-attention. The strength of vanilla Transformers lies in modeling cross-modality global feature correlations. However, such mechanisms often struggle with the structural disparity between dense image pixels and sparse 3D points, hindering the establishment of fine-grained correspondences. Moreover, global attention may introduce ambiguity, as interactions with many inconsistent regions of intra-modality may degrade feature distinctiveness. To address these …

Exploring Neural Network Structure Code Reuse In The Open-Source Community For Improving Maintenance, Xiaoning Ren, Yuekun Wang, Chongyang Liu, Yueming Wu, Qiang Hu, Lijun Zhang, Yinxing Xue

Research Collection School Of Computing and Information Systems

Neural networks (NNs) have rapidly advanced, demonstrating exceptional performance across various fields, leading to a surge in open-source NN projects. The complexity and rapid growth of these projects pose significant challenges for maintenance within the open-source community. Given that NN architecture code is the core asset of NN projects, understanding its reuse in the open-source community is essential for effective maintenance, such as reducing redundancy and identifying potential intellectual property violations. While prior studies have examined code reuse in open-source projects, they have two key limitations: They do not specifically address NN structure code, and they rely on manually selected …

Compositions Of Variant Experts For Integrating Short-Term And Long-Term Preferences, Dinh Hieu Do, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

In the online digital realm, recommendation systems are ubiquitous and play a crucial role in enhancing user experience. These systems leverage user preferences to provide personalized recommendations, thereby helping users navigate through the paradox of choice. This work focuses on personalized sequential recommendation, where the system considers not only a user’s immediate, evolving session context, but also their cumulative historical behavior to provide highly relevant and timely recommendations. Through an empirical study conducted on diverse real-world datasets, we have observed and quantified the existence and impact of both short-term (immediate and transient) and long-term (enduring and stable) preferences on users’ …

A Novel Privacy-Preserving User Information Queries Scheme With Functional Policy, Yuhang Lei, Rui Shi, Yang Yang, Chunjie Cao, Huamin Feng

Research Collection School Of Computing and Information Systems

Privacy-preserving information queries enable a requester to obtain only the value f(x) computed over sensitive data x, while preventing disclosure of the underlying records. Existing approaches typically reveal full data, incur high on-chain overhead, or lack fair and verifiable delivery of function outputs. We propose a general-purpose, blockchain-compatible framework that ensures the requester learns only f(x) with no extra leakage and that the provider receives fair payment. The design integrates Adaptor Signatures (AS) for fair exchange and Inner-Product Functional Encryption (IPFE) for fine-grained function extraction. The framework is domain-agnostic and applicable to privacy-sensitive applications such as medical insurance and financial …

How Intellectual Humility Enhances Affective Well-Being: Daily Diary Studies On The Mediating Roles Of Daily Uplift And Stressor Exposure, Ysabel A. Guevarra, K. T. A. Sandeeshwara Kasturiratna, Andree Hartanto, Eddie M. W. Tong, Verity Y. Q. Lua, Nadyanna M. Majeed

Research Collection School of Social Sciences

Objective: While intellectual humility has gained increasing prominence as a cognitive construct, its implications for affective well-being remain less understood. Method: The present paper draws on 7-day daily diary datasets (Study 1: Nparticipants=253, Nobservations=1721; Study 2: Nparticipants=485, Nobservations=3218) to examine how trait intellectual humility relates to daily positive and negative affect during uplifting and stressful events. We also tested potential mechanisms underlying the link between intellectual humility and affective well-being by examining whether intellectual humility moderates affective reactions to daily events or whether it indirectly enhances affective well-being by influencing the frequency of daily uplift and stressor exposure. Results: Across …