Computer Sciences Commons^™

A Functional Software Reference Architecture For Llm-Integrated Systems, Alessio Bucaioni, Martin Weyssow, Junda He, Yunbo Lyu, David Lo

Research Collection School Of Computing and Information Systems

The integration of large language models into software systems is transforming capabilities such as natural language understanding, decision-making, and autonomous task execution. However, the absence of a commonly accepted software reference architecture hinders systematic reasoning about their design and quality attributes. This gap makes it challenging to address critical concerns like privacy, security, modularity, and interoperability, which are increasingly important as these systems grow in complexity and societal impact. In this paper, we describe our emerging results for a preliminary functional reference architecture as a conceptual framework to address these challenges and guide the design, evaluation, and evolution of large …

Digital Transformation And The Future Of Work: Closing The Digital Skills Gap, Siu Loon Hoe

Research Collection School Of Computing and Information Systems

The purpose of this article is to discuss the near future digital technology landscape and propose several specific in-demand digital skills for organizations and individuals in the next few years. This article reviews some recent publications from representative inter-governmental, governmental, non-governmental, and commercial organizations on the rise of digital technologies and corresponding growth in digital jobs. Within this context, several specific in-demand skills are proposed by the author who has written a book on the topic of digital transformation. Rapid advancements in digital technologies continue to shape organizational practices and the future of work. To take advantage of emerging digital …

Use Of Search Tools In Software Development: A Study Of Microservice-Based Team Projects, Yi Meng Lau, Christian Michael Koh, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Universities are increasingly integrating real-world projects into software engineering curricula to preparestudents for careers involving complex concepts like Microservices Architecture (MSA). Students frequentlystruggle with such concepts within limited class time and turn to various search tools and online resources for additional help. Search tools are also widely used in the software development industry. While search engines, like Google and Yahoo!, can provide quick solutions, they pose the risk of information overload. Large Language Models (LLMs) such as ChatGPT, offer the advantage of delivering more precise answers. Studies have shown that LLMs can comprehend codes, assist in system architectural design, and …

Frame-Voyager: Learning To Query Frames For Video Large Language Models, Sicheng Yu, Chengkai Jin, Huanyu Wang, Zhenghao Chen, Sheng Jin, Zhongrong Zuo, Xiaolei Xu, Zhenbang Sun, Bingni Zhang, Jiawei Wu, Hao Zhang, Qianru Sun

Research Collection School Of Computing and Information Systems

Video Large Language Models (Video-LLMs) have made remarkable progress in video understanding tasks. However, they are constrained by the maximum length of input tokens, making it impractical to input entire videos. Existing frame selection approaches, such as uniform frame sampling and text-frame retrieval, fail to account for the information density variations in the videos or the complex instructions in the tasks, leading to sub-optimal performance. In this paper, we propose Frame-Voyager that learns to query informative frame combinations, based on the given textual queries in the task. To train Frame-Voyager, we introduce a new data collection and labeling pipeline, by …

Enmob: Unveil The Behavior With Multi-Flow Analysis Of Encrypted App Traffic, Mengmeng Ge, Ruitao Feng, Likun Liu, Xiangzhan Yu, Sachidananda Vinay, Xiaofei Xie, Yang Liu

Research Collection School Of Computing and Information Systems

In the contemporary digital landscape, mobile applications have become the predominant conduit for internet connectivity and daily tasks. Simultaneously, the advent of application encryption technology has safeguarded users’ privacy. However, this encryption, while fortifying privacy, introduces challenges to security by hindering the effective management of network applications within encrypted data streams. Conventional detection methods for encrypted application traffic, relying heavily on statistical metrics like payload, packet size, and distribution, are constrained to single traffic flows, often yielding results of limited specificity. To address this limitation, our paper introduces an innovative approach that elucidates the multi-flow nature of application behavior traffic …

Marginal Benefit Driven Rl Teacher For Unsupervised Environment Design, Dexun Li, Wenjun Li, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Training generally capable agents in complex environments is a challenging task that involves identifying the “right” environments at the training stage. Recent research has highlighted the potential of the Unsupervised Environment Design framework, which generates environment instances/levels adaptively at the frontier of the agent’s capabilities using regret measures. While regret approaches have shown promise in generating feasible environments, they can produce difficult environments that are challenging for an RL agent to learn from. This is because regret represents the best-case (upper bound) learning potential and not the actual learning potential of an environment. To address this, we propose an alternative …

Why Ai’S Role In Advancing Sustainability Is Underestimated, Lipika Bhattacharya

CCX Research

AI has quietly, but powerfully, woven itself into the fabric of our everyday lives. Yet, AI's potential impact on creating a more sustainable world is undervalued. The author examined artificial intelligence's (AI) role in advancing sustainability. She outlined how AI can be applied in various domains such as agriculture, water management, industry, urban planning, and biodiversity conservation for transformative effects.

Learning: Human Versus Machine, Sanjay Sarma

Asian Management Insights

Outdated education paradigms must be revamped to reclaim the all-important human quality: agency.

Sanjay Sarma, CEO, President, and Dean of the Asia School of Business, Kuala Lumpur, Malaysia and the Fred Fort Flowers (1941) and Daniel Fort Flowers (1941) Professor in Mechanical Engineering at the Massachusetts Institute of Technology (MIT), shares insights on the artificial intelligence (AI)-agency revolution and how the human brain works.

The Ethics Of Ai Nudges: How Ai Influences Decision-Making, Seema Chokshi

Asian Management Insights

And why decision-makers should care about it. Artificial intelligence (AI) systems, through mechanisms like nudges and choice architecture, actively, yet often subtly, shape human decision-making in everyday life and professional settings. AI systems can prioritise profit or efficiency at the expense of human agency, fairness, and well-being, highlighting the need to balance AI’s capabilities with ethical considerations. The EU AI Act is a landmark framework designed to curb manipulative AI practices, emphasising the protection of human autonomy and accountability in decision-making.

Reimagining Education: Keeping The Human In The Loop, Pradeep Varakantham, Sidney Tio

Asian Management Insights

How educators can work with generative artificial intelligence models to improve learning. Artificial intelligence (AI) helps break the mould of one-size-fits-all education by creating personalised learning paths that adapt to each student’s pace and style. By combining human expertise with AI capabilities, educators can create learning experiences that are both structured and flexible, thus getting the best of both worlds. While promising, AI used in educational contexts must carefully navigate privacy concerns, ensure fairness across all student groups, and support appropriate learning progression.

Generalization Analysis For Deep Contrastive Representation Learning, Minh Hieu Nong, Antoine Ledent, Yunwen Lei, Cheng Yeaw Ku

Research Collection School Of Computing and Information Systems

In this paper, we present generalization bounds for the unsupervised risk in the Deep Contrastive Representation Learning framework, which employs deep neural networks as representation functions. We approach this problem from two angles. On the one hand, we derive a parameter-counting bound that scales with the overall size of the neural networks. On the other hand, we provide a norm-based bound that scales with the norms of neural networks’ weight matrices. Ignoring logarithmic factors, the bounds are independent of k, the size of the tuples provided for contrastive learning. To the best of our knowledge, this property is only shared …

How To Securely Delegate And Revoke Partial Authorization Credentials, Meng Sun, Junzuo Lai, Wei Wu, Ye Yang, Cheng-Kang Chu, Robert H. Deng

Research Collection School Of Computing and Information Systems

An attribute-based credential (ABC) system allows a user, obtaining a credential on a set of attributes from an issuer, to anonymously prove a subset of attributes to a service provider. Nowadays, delegation is an important requirement of ABC, which allows a user to delegate his credentials to other users. However, traditional delegatable ABC systems only support delegating a credential with all attributes. In many scenarios, an appropriate delegation is a user can delegate his credential on parts of attributes to others. Another requirement is revocation of credentials in case of unexpected events. In this article, we propose a delegatable and …

Exploring Intelligent Manufacturing: How Artificial Intelligence Affects Productivity And Labor Demand At The Enterprise Level, Jie Gu

Dissertations and Theses Collection (Open Access)

Manufacturing is a cornerstone of national economic health and social stability, yet it faces challenges such as declining profits, rising labor costs, and an aging workforce. In China, the manufacturing sector is undergoing a critical transformation, driven by technological advancements like artificial intelligence (AI) and the push for intelligent manufacturing. This study explores how AI revitalizes the manufacturing sector by enhancing enterprise productivity and reshaping labor demand, with a focus on quality inspection processes. Using a leading bearing factory as a case study, the research employs econometric models, A/B testing, and interviews to quantify AI’s impact on production efficiency, costs, …

Learning To Identify Seen, Unseen And Unknown In The Open World: A Practical Setting For Zero-Shot Learning, Sethupathy Parameswaran, Yuan Fang, Chandan Gautam, Savitha Ramasamy, Xiaoli Li

Research Collection School Of Computing and Information Systems

As vision-language models advance, addressing the Zero-Shot Learning (ZSL) problem in the open world becomes increasingly crucial. Specifically, a robust model must handle three types of samples during inference: seen classes with visual and semantic information provided in training, unseen classes with only the semantic information in training, and unknown samples with no prior information from training. Existing methods either handle seen and unseen classes together (ZSL) or seen and unknown classes (known as Open-Set Recognition, OSR). However, none addresses the simultaneous handling of all three, which we term Open-Set Zero-Shot Learning (OZSL). To address this problem, we propose a …

Divide-And-Conquer: Confluent Triple-Flow Network For Rgb-T Salient Object Detection, Hao Tang, Zechao Li, Dong Zhang, Shengfeng He, Jinhui Tang

Research Collection School Of Computing and Information Systems

RGB-Thermal Salient Object Detection (RGB-T SOD) aims to pinpoint prominent objects within aligned pairs of visible and thermal infrared images. A key challenge lies in bridging the inherent disparities between RGB and Thermal modalities for effective saliency map prediction. Traditional encoder-decoder architectures, while designed for cross-modality feature interactions, may not have adequately considered the robustness against noise originating from defective modalities, thereby leading to suboptimal performance in complex scenarios. Inspired by hierarchical human visual systems, we propose the ConTriNet, a robust Confluent Triple-Flow Network employing a "Divide-and-Conquer"strategy. This framework utilizes a unified encoder with specialized decoders, each addressing different subtasks …

Selecting Comparative Sets Of Reviews Across Multiple Items, Trung Hoang Le, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

While choosing among several products, users may look up reviews from each product they are considering. Due to the large number of reviews of products, selecting representative reviews from one product alone is already a challenging problem. In this work, we further aim to conduct review selection for multiple products simultaneously for comparative purposes. We formulate objective functions that synchronize the review selection and design efficient algorithms to optimize for the objective functions. To narrow down the potentially long list of comparison items into a shorter list of more similar items, we construct a graph representing items’ similarity and design …

Mimic: Ai And Ar-Enhanced Multi-Modal, Immersive, Relative Instruction Comprehension, Dhanuja Wanniarachchi, Archan Misra

Research Collection School Of Computing and Information Systems

We present a multimodal instruction comprehension framework, called MImIC, that utilizes visual sensing (including LIDAR and 2D RGB sensing) & AI spatial reasoning capabilities to support more seamless and immersive interaction between humans and AI-driven situated assistive agents. MImIC's key new capability is to support disambiguation of a wider set of relative spatial references that users naturally employ while issuing spatially-situated instructions. To support enhanced visual grounding via a combination of both fully-qualified and relative attribute references, MImIC uses (a) a fine-tuned transformer-based language translation DNN to accurately convert natural verbal commands into a structured set of machine understandable constraints …

Explainable Neural Networks With Guarantee: A Sparse Estimation Approach, Antoine Ledent, Peng Liu

Research Collection School Of Computing and Information Systems

Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel approach to constructing an explainable neural network that harmonizes predictiveness and explainability. Our model is designed as a linear combination of a sparse set of jointly learned features, each derived from a different trainable function applied to a single 1-dimensional input feature. Leveraging the ability to learn arbitrarily complex relationships, our neural network architecture enables automatic selection of a sparse set of important features, with the final prediction being …

Multisfl: Towards Accurate Split Federated Learning Via Multi-Model Aggregation And Knowledge Replay, Zeke Xia, Ming Hu, Dengke Yan, Ruixuan Liu, Anran Li, Xiaofei Xie, Mingsong Chen

Research Collection School Of Computing and Information Systems

Although Split Federated Learning (SFL) effectively enables knowledge sharing among resource-constrained clients, it suffers from low training performance due to the neglect of data heterogeneity and catastrophic forgetting problems. To address these issues, we propose a novel SFL approach named MultiSFL, which adopts i) an effective multimodel aggregation mechanism to alleviate gradient divergence caused by heterogeneous data and ii) a novel knowledge replay strategy to deal with the catastrophic forgetting problem. MultiSFL adopts two servers (i.e., the fed server and main server) to maintain multiple branch models for local training and an aggregated master model for knowledge sharing among branch …

Understanding Individual Agent Importance In Multi-Agent System Via Counterfactual Reasoning, Jianming Chen, Yawen Wang, Junjie Wang, Xiaofei Xie, Jun Hu, Qing Wang, Fanjiang Xu

Research Collection School Of Computing and Information Systems

Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has provided explanations for the actions or states of agents, yet falls short in understanding the black-boxed agent's importance within a MAS and the overall team strategy. To bridge this gap, we propose EMAI, a novel agent-level explanation approach that evaluates the individual agent's importance. Inspired by counterfactual reasoning, a larger change in reward caused by the randomized action of agent indicates its higher importance. We model it as a MARL problem to capture interactions across agents. Utilizing counterfactual reasoning, EMAI learns the …

Lightprof: A Lightweight Reasoning Framework For Large Language Model On Knowledge Graph, Tu Ao, Yanhua Yu, Yuling Wang, Yang Deng, Zirui Guo, Liang Pang, Pinghui Wang, Tat-Seng Chua, Xiao Zhang, Zhen Cai

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have impressive capabilities in text understanding and zero-shot reasoning. However, delays in knowledge updates may cause them to reason incorrectly or produce harmful results. Knowledge Graphs (KGs) provide rich and reliable contextual information for the reasoning process of LLMs by structurally organizing and connecting a wide range of entities and relations. Existing KG-based LLM reasoning methods only inject KGs’ knowledge into prompts in a textual form, ignoring its structural information. Moreover, they mostly rely on close-source models or open-source models with large parameters, which poses challenges to high resource consumption. To address this, we propose a …

Aligning Large Language Models For Faithful Integrity Against Opposing Argument, Yong Zhao, Yang Deng, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. However, they can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. To this end, we investigate the problem of maintaining faithful integrity in LLMs. This involves ensuring that LLMs adhere to their faithful statements in the face of opposing arguments and are able to correct their incorrect statements when presented with faithful arguments. In this work, we propose a novel framework, named Alignment for Faithful Integrity with Confidence Estimation (AFICE), which aims to align the LLM responses with faithful integrity. Specifically, …

Fully Selective Opening Secure Ibe From Lwe, Dingding Jia, Haiyang Xue, Bao Li

Research Collection School Of Computing and Information Systems

Selective opening security ensures that, when an adversary is given multiple ciphertexts and corrupts a subset of the senders (thereby obtaining the plaintexts and the senders’ randomness), the privacy of the remaining ciphertexts is still preserved. Previous selective opening secure IBE schemes encrypt messages bit-by-bit, or only achieve selective-id security. In this paper, we present the first adaptive-id, selective opening secure identity-based encryption (IBE) tightly from LWE. To achieve this, we introduce a new primitive called delegatable all-but-many lossy trapdoor functions (DABM-LTDF) and provide a generic construction that converts DABM-LTDF into an adaptive-id, selective opening secure IBE through a tight …

Personamagic: Stage-Regulated High-Fidelity Face Customization With Tandem Equilibrium, Xinzhe Li, Jiahui Zhan, Shengfeng He, Yangyang Xu, Junyu Dong, Huaidong Zhang, Yong Du

Research Collection School Of Computing and Information Systems

Personalized image generation has made significant strides in adapting content to novel concepts. However, a persistent challenge remains: balancing the accurate reconstruction of unseen concepts with the need for editability according to the prompt, especially when dealing with the complex nuances of facial features. In this study, we delve into the temporal dynamics of the text-to-image conditioning process, emphasizing the crucial role of stage partitioning in introducing new concepts. We present PersonaMagic, a stage-regulated generative technique designed for high-fidelity face customization. Using a simple MLP network, our method learns a series of embeddings within a specific timestep interval to capture …

An Aspect Performance-Aware Hypergraph Neural Network For Review-Based Recommendation, Junrui Liu, Tong Li, Di Wu, Zifang Tang, Yuan Fang, Zhen Yang

Research Collection School Of Computing and Information Systems

Online reviews allow consumers to provide detailed feedback on various aspects of items. Existing methods utilize these aspects to model users' fine-grained preferences for specific item features through graph neural networks. We argue that the performance of items on different aspects is important for making precise recommendations, which has not been taken into account by existing approaches, due to lack of data. In this paper, we propose an aspect performance-aware hypergraph neural network (APH) for the review-based recommendation, which learns the performance of items from the conflicting sentiment polarity of user reviews. Specifically, APH comprehensively models the relationships among users, …

Simulation-Free Hierarchical Latent Policy Planning For Proactive Dialogues, Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Yiheng Sun, Zerui Chen, Ming Liu, Bing Qin

Research Collection School Of Computing and Information Systems

Recent advancements in proactive dialogues have garnered significant attention, particularly for more complex objectives (e.g. emotion support and persuasion). Unlike traditional task-oriented dialogues, proactive dialogues demand advanced policy planning and adaptability, requiring rich scenarios and comprehensive policy repositories to develop such systems. However, existing approaches tend to rely on Large Language Models (LLMs) for user simulation and online learning, leading to biases that diverge from realistic scenarios and result in suboptimal efficiency. Moreover, these methods depend on manually defined, context-independent, coarse-grained policies, which not only incur high expert costs but also raise concerns regarding their completeness. In our work, we …

Unlocking The Potential Of Black-Box Pre-Trained Gnns For Graph Few-Shot Learning, Qiannan Zhang, Shichao Pei, Yuan Fang, Xiangliang Zhang

Research Collection School Of Computing and Information Systems

Few-shot learning has emerged as an important problem on graphs to combat label scarcity, which can be approached by current trends in pre-trained graph neural networks (GNNs) and meta-learning. Recent efforts integrate both paradigms in a white-box setting, leaving the more realistic black-box setting largely underexplored, where the parameters and gradients in the pre-trained GNNs are inaccessible. In this paper, we study the critical problem: Leveraging black-box pre-trained GNNs for graph few-shot learning. Despite its appeal, two key issues hinder the unlocking of its potential: the inherent task gap between pre-training and downstream stages, which can introduce irrelevant knowledge and …

Dr. Tongue: Sign-Oriented Multi-Label Detection For Remote Tongue Diagnosis, Yiliang Chen, Steven S. C. Ho, Cheng Xu, Yao Jie Xie, Wing Fai Yeung, Shengfeng He, Jing Qin

Research Collection School Of Computing and Information Systems

Tongue diagnosis is a vital tool in Western and Traditional Chinese Medicine, providing key insights into a patient's health by analyzing tongue attributes. The COVID-19 pandemic has heightened the need for accurate remote medical assessments, emphasizing the importance of precise tongue attribute recognition via telehealth. To address this, we propose a Sign-Oriented multi-label Attributes Detection framework. Our approach begins with an adaptive tongue feature extraction module that standardizes tongue images and mitigates environmental factors. This is followed by a Sign-oriented Network (SignNet) that identifies specific tongue attributes, emulating the diagnostic process of experienced practitioners and enabling comprehensive health evaluations. To …

Understanding The Oss Communities Of Deep Learning Frameworks: A Comparative Case Study Of Pytorch And Tensorflow, Yunqi Chen, Zhiyuan Wan, Yifei Zhuang, Ning Liu, David Lo, Xiaohu Yang

Research Collection School Of Computing and Information Systems

Over the past two decades, deep learning has received tremendous success in developing software systems across various domains. Deep learning frameworks have been proposed to facilitate the development of such software systems, among which, PyTorch and TensorFlow stand out as notable examples. Considerable attention focuses on exploring software engineering practices and addressing diverse technical aspects in developing and deploying deep learning frameworks and software systems. Despite these efforts, little is known about the open source software communities involved in the development of deep learning frameworks. In this article, we perform a comparative investigation into the open source software communities of …

Varium: Variational Autoencoder For Multi-Interest Representation With Inter-User Memory, Nhu Thuat Tran, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Frameworks for discovering multiple user interest factors based on Variational AutoEncoder (VAE) has demonstrated competitive recommendation performance. However, as VAE only considers one user as input at a time, sharing across like-minded users may not be adequately facilitated. Moreover, interest sharing between users is not always available and thus, poses a challenge for VAE to explicitly model this information. To resolve this, we introduce an inter-user memory-based mechanism to unsupervisedly discover latent interest sharing between users under VAE framework. Concretely, we design a memory including an array of prototypes, each hypothetically representing a group of users sharing a particular interest. …