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

Digital Commons Network™

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

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 601 - 630 of 10474

Full-Text Articles in Entire DC Network

Freqllm: Frequency-Aware Large Language Models For Time Series Forecasting, Shunan Wang, Min Gao, Zongwei Wang, Yibing Bai, Feng Jiang, Guansong Pang Aug 2025

Freqllm: Frequency-Aware Large Language Models For Time Series Forecasting, Shunan Wang, Min Gao, Zongwei Wang, Yibing Bai, Feng Jiang, Guansong Pang

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have recently shown promise in Time Series Forecasting (TSF) by effectively capturing intricate time-domain dependencies. However, our preliminary experiments reveal that standard LLM-based approaches often fail to capture global correlations, limiting predictive performance. We found that embedding frequency-domain signals smooths weight distributions and enhances structured correlations by clearly separating global trends (low-frequency components) from local variations (high-frequency components). Building on these insights, we propose FreqLLM, a novel framework that integrates frequency-domain semantic alignment into LLMs to refine prompts for improved time series analysis. By bridging the gap between frequency signals and textual embeddings, FreqLLM effectively captures …

Go to article

Fine‑Tuning Multimodal Large Language Models For Product Bundling, Xiaohao Liu, Jie Wu, Zhulin Tao, Yunshan Ma, Yinwei Wei, Tat-Seng Chua Aug 2025

Fine‑Tuning Multimodal Large Language Models For Product Bundling, Xiaohao Liu, Jie Wu, Zhulin Tao, Yunshan Ma, Yinwei Wei, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Recent advances in product bundling have leveraged multimodal information through sophisticated encoders, but remain constrained by limited semantic understanding and a narrow scope of knowledge. Therefore, some attempts employ In-context Learning (ICL) to explore the potential of large language models (LLMs) for their extensive knowledge and complex reasoning abilities. However, these efforts are inadequate in understanding mulitmodal data and exploiting LLMs' knowledge for product bundling. To bridge the gap, we introduce Bundle-MLLM, a novel framework that fine-tunes LLMs through a hybrid item tokenization approach within a well-designed optimization strategy. Specifically, we integrate textual, media, and relational data into a unified …

Go to article

Anomalygfm: Graph Foundation Model For Zero/Few-Shot Anomaly Detection, Hezhe Qiao, Chaoxi Niu, Ling Chen, Guansong Pang Aug 2025

Anomalygfm: Graph Foundation Model For Zero/Few-Shot Anomaly Detection, Hezhe Qiao, Chaoxi Niu, Ling Chen, Guansong Pang

Research Collection School Of Computing and Information Systems

Graph anomaly detection (GAD) aims to identify abnormal nodes that differ from the majority of the nodes in a graph, which has been attracting significant attention in recent years. Existing generalist graph models have achieved remarkable success in different graph tasks but struggle to generalize to the GAD task. This limitation arises from their difficulty in learning generalized knowledge for capturing the inherently infrequent, irregular and heterogeneous abnormality patterns in graphs from different domains. To address this challenge, we propose AnomalyGFM, a GAD-oriented graph foundation model that supports zero-shot inference and few-shot prompt tuning for GAD in diverse graph datasets. …

Go to article

Affinitytune: A Prompt-Tuning Framework For Few-Shot Anomaly Detection On Graphs, Jingyan Chen, Guanghui Zhu, Guansong Pang, Chunfeng Yuan, Yihua Huang Aug 2025

Affinitytune: A Prompt-Tuning Framework For Few-Shot Anomaly Detection On Graphs, Jingyan Chen, Guanghui Zhu, Guansong Pang, Chunfeng Yuan, Yihua Huang

Research Collection School Of Computing and Information Systems

Graph anomaly detection (GAD) is a critical task with applications in domains such as networking, finance, and bioinformatics. % However, the scarcity of labeled anomalies and the limitations of unsupervised methods hinder effective detection. % While semi-supervised and few-shot learning approaches offer improvements, they struggle with knowledge transfer and rely heavily on labeled data. % Recent advancements in prompt tuning on graphs provide a promising direction, but their application to heterophilous graphs in anomaly detection remains underexplored. % In this work, we propose AffinityTune, a novel framework for few-shot graph anomaly detection based on prompt tuning. % Our approach introduces …

Go to article

Llm2rec: Large Language Models Are Powerful Embedding Models For Sequential Recommendation, Yingzhi He, Xiaohao Liu, An Zhang, Yunshan Ma, Tat‑Seng Chua Aug 2025

Llm2rec: Large Language Models Are Powerful Embedding Models For Sequential Recommendation, Yingzhi He, Xiaohao Liu, An Zhang, Yunshan Ma, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Sequential recommendation aims to predict users' future interactions by modeling collaborative filtering (CF) signals from historical behaviors of similar users or items. Traditional sequential recommenders predominantly rely on ID-based embeddings, which capture CF signals through high-order co-occurrence patterns. However, these embeddings depend solely on past interactions, lacking transferable knowledge to generalize to unseen domains. Recent advances in large language models (LLMs) have motivated text-based recommendation approaches that derive item representations from textual descriptions. While these methods enhance generalization, they fail to encode CF signals-i.e., latent item correlations and preference patterns-crucial for effective recommendation. We argue that an ideal embedding model …

Go to article

Collisionrepair: First‑Aid And Automated Patching For Storage Collision Vulnerabilities In Smart Contracts, Yu Pan, Wanjing Han, Yue Duan, Mu Zhang Aug 2025

Collisionrepair: First‑Aid And Automated Patching For Storage Collision Vulnerabilities In Smart Contracts, Yu Pan, Wanjing Han, Yue Duan, Mu Zhang

Research Collection School Of Computing and Information Systems

Storage collision vulnerabilities, a significant security risk in upgradeable smart contracts, often arise when a user-facing proxy contract and a backend logic contract share storage space. While static analysis techniques can detect such issues, they often over-approximate program states, leading to false positives and requiring developers to manually verify each issue, giving attackers time to exploit any overlooked vulnerabilities. To address this, we propose COLLISIONREPAIR, an automated patching technique for mitigating storage collision risks. COLLISIONREPAIR monitors storage access sequences between proxy and logic contracts by defining an "ownership" property for storage locations. It then replays historical transactions to recover existing …

Go to article

Prism: To Fortify Widget Based User‑App Data Exchanges Using Android Virtualization Framework, Yingtat Ng, Zhe Chen, Haiqing Qiu, Xuhua Ding Aug 2025

Prism: To Fortify Widget Based User‑App Data Exchanges Using Android Virtualization Framework, Yingtat Ng, Zhe Chen, Haiqing Qiu, Xuhua Ding

Research Collection School Of Computing and Information Systems

We present Prism, an UI hardening technique for an Android app to safeguard its widgets against a corrupted kernel. Prism ensures secure interface rendering and allows for visual authentication, which developers could use to enable user intent confidentiality protection. Our design leverages the recent Android Virtualization Framework with minimal changes to the existing UI framework and graphics subsystem. It is much easier to deploy and use Prism on Android phones than TrustZone-based secure UI schemes, because the apps are not admitted to the Secure World and retain their full rights to manage and control their own interfaces. We have implemented …

Go to article

Achilles: A Formal Framework Of Leaking Secrets From Signature Schemes Via Rowhammer, Junkai Liang, Zhi Zhang, Xin Zhang, Qingni Sheng, Yansong Gao, Xinliang Yuan, Haiyang Xue, Pengfei Wu, Zhonghai. Wu Aug 2025

Achilles: A Formal Framework Of Leaking Secrets From Signature Schemes Via Rowhammer, Junkai Liang, Zhi Zhang, Xin Zhang, Qingni Sheng, Yansong Gao, Xinliang Yuan, Haiyang Xue, Pengfei Wu, Zhonghai. Wu

Research Collection School Of Computing and Information Systems

Signature schemes are a fundamental component of cyber-security infrastructure. While they are designed to be mathematically secure against cryptographic attacks, they are vulnerable to Rowhammer fault-injection attacks. Since all existing attacks are ad-hoc in that they target individual parameters of specific signature schemes, it remains unclear about the impact of Rowhammer on signature schemes as a whole.In this paper, we present Achilles, a formal framework that aids in leaking secrets in various real-world signature schemes via Rowhammer. Particularly, Achilles can be used to find potentially more vulnerable parameters in schemes that have been studied before and also new schemes that …

Go to article

Exploring Rehabilitation Therapists' Knowledge And Perspectives On The Use Of Artificial Intelligence And Machine Learning For Persons Poststroke, Hannah Clark, Mia Delvecchio, Min Hun Lee, Elena D. Brown, Kaia Mikula, Robert Halyama, Kasey Stepansky Aug 2025

Exploring Rehabilitation Therapists' Knowledge And Perspectives On The Use Of Artificial Intelligence And Machine Learning For Persons Poststroke, Hannah Clark, Mia Delvecchio, Min Hun Lee, Elena D. Brown, Kaia Mikula, Robert Halyama, Kasey Stepansky

Research Collection School Of Computing and Information Systems

Research Objectives: The use of technology such as robotics, gaming systems, self-monitoring apps, or other sensor-based devices in standard practice is infrequent. Due to the rapid development of artificial intelligence (AI) and machine learning (ML) applications, it is important to look at how therapists perceive AI/ML, and design applications with potential barriers in mind. to support future integration into practice. The purpose of this research project is to gain rehabilitation therapists’ perspectives on AI/ML in post-stroke assessment and intervention.Design: This ongoing study uses a mixed methods design with surveys and focus groups. Participants engaged in a 30-minute webinar to learn …

Go to article

Faced With Genai, Educators’ Engagement Capacity Matters More Than Ever, Thomas Menkhoff Aug 2025

Faced With Genai, Educators’ Engagement Capacity Matters More Than Ever, Thomas Menkhoff

Research Collection Lee Kong Chian School Of Business

In a commentary, SMU Professor of Organisational Behaviour & Human Resources (Education) Thomas Menkhoff stressed the need for educators to upskill so they can guide students in using generative artificial intelligence (GenAI) responsibly, rather than dismissing it. He argued that universities should move beyond prohibition and invest in AI literacy to safeguard academic integrity. Prof Menkhoff mentioned that combining the use of GenAI tools with effective prompting and Socratic questioning transforms students’ use of technology from passive consumption to active, reflective and critical engagement. To achieve this, he said that schools must set clear guidelines and design AI-compatible assessments that …

Go to article

Eliciting Supplier Cooperation For Value Chain Decarbonization: A Field Experiment With Smallholder Farmers In India, Sukti Ghosh, Jasjit Singh Aug 2025

Eliciting Supplier Cooperation For Value Chain Decarbonization: A Field Experiment With Smallholder Farmers In India, Sukti Ghosh, Jasjit Singh

Research Collection Lee Kong Chian School Of Business

Many firms are attempting to reduce greenhouse gas emissions across their value chain. However, this requires convincing suppliers to adopt relevant decarbonization practices, which is challenging when the suppliers perceive such practices as risky or detrimental for their economic well-being. We employ a field experiment to examine relational investments (i.e., investments intended to promote mutual benefit for the exchange partners) as a tool for overcoming this challenge. In a research collaboration with a global firm pursuing decarbonization of its agricultural supply chain in India, we investigated the effectiveness of complementing training their supplier farmers on climate-friendly agricultural practices with also …

Go to article

Not All Political Ties Are The Same: Firms' Ties To The Government And Pollution, Wen Helena Li, Ilya R. P. Cuypers, Gokhan Ertug, Hari Bapuji, Wei Liu Aug 2025

Not All Political Ties Are The Same: Firms' Ties To The Government And Pollution, Wen Helena Li, Ilya R. P. Cuypers, Gokhan Ertug, Hari Bapuji, Wei Liu

Research Collection Lee Kong Chian School Of Business

Complementing research on the implications of political ties for firms’ strategic decisions and financial performance, recent studies are increasingly focusing on the environmental consequences of firms’ political connections. We contribute to this stream of work by integrating insights from the literature on political ties and the multifaceted nature of governments to explore how the level of government influences the pollution implications of firms’ political ties. Specifically, we theorize and demonstrate that, in China, firms' achieved political ties with high levels of the government reduce pollution, while such ties with low levels of the government increase it. Furthermore, we examine how …

Go to article

On The Origin Of Green Finance Policies, Theodor Florian Cojoianu, D. French, Andrea G. F. Hoepner, Sheenan L., Anh Vu Aug 2025

On The Origin Of Green Finance Policies, Theodor Florian Cojoianu, D. French, Andrea G. F. Hoepner, Sheenan L., Anh Vu

Research Collection College of Integrative Studies

Despite the rising number of green finance policies, the socioeconomic determinants shaping them remain largely unexamined. Drawing from the literature analysing the relationship between regulation, market development and institutional economics, we contend that green finance policy adoption is driven by both market-based and institutional factors. Using a survival analysis approach to understand the levers influencing green finance policy adoption across 188 countries from 2000 to 2019, we find that exposure to the fossil fuel industry predominantly drives the initial issuance of green finance policies. The positive effect of fossil fuel commercial financing on the adoption of green finance policies exists …

Go to article

Gcot: Chain-Of-Thought Prompt Learning For Graphs, Xingtong Yu, Chang Zhou, Zhongwei Kuai, Xinming Zhang, Yuan Fang Aug 2025

Gcot: Chain-Of-Thought Prompt Learning For Graphs, Xingtong Yu, Chang Zhou, Zhongwei Kuai, Xinming Zhang, Yuan Fang

Research Collection School Of Computing and Information Systems

Chain-of-thought (CoT) prompting has achieved remarkable success in natural language processing (NLP). However, its vast potential remains largely unexplored for graphs. This raises an interesting question: How can we design CoT prompting for graphs to guide graph models to learn step by step? On one hand, unlike natural languages, graphs are non-linear and characterized by complex topological structures. On the other hand, many graphs lack textual data, making it difficult to formulate language-based CoT prompting. %Therefore we cannot directly adopt the CoT prompting methods used in the language domain. In this work, we propose the first CoT prompt learning framework …

Go to article

Quantizing Text-Attributed Graphs For Semantic-Structural Integration, Jianyuan Bo, Hao Wu, Yuan Fang Aug 2025

Quantizing Text-Attributed Graphs For Semantic-Structural Integration, Jianyuan Bo, Hao Wu, Yuan Fang

Research Collection School Of Computing and Information Systems

Text-attributed graphs (TAGs) have emerged as a powerful representation for modeling complex relationships across diverse domains. With the rise of large language models (LLMs), there is growing interest in leveraging their capabilities for graph learning. However, current approaches face significant challenges in embedding structural information into LLM-compatible formats, requiring either computationally expensive alignment mechanisms or manual graph verbalization techniques that often lose critical structural details. Moreover, these methods typically require labeled data from source domains for effective transfer learning, significantly constraining their adaptability. We propose STAG, a novel self-supervised framework that directly quantizes graph structural information into discrete tokens using …

Go to article

The 6th International Workshop On Talent And Management Computing (Tmc 2025), Hengshu Zhu, Yong Ge, Hui Xiong, Ee-Peng Lim Aug 2025

The 6th International Workshop On Talent And Management Computing (Tmc 2025), Hengshu Zhu, Yong Ge, Hui Xiong, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

In today's competitive and fast-evolving business environment, it is a critical time for organizations to rethink how to deal with talent and management-related tasks in a quantitative manner. Indeed, thanks to the era of big data, the availability of large-scale talent data provides unparalleled opportunities for leaders to deliver intelligence for effective management for organizations. In the past few years, talent and management computing have increasingly attracted attention from KDD communities, and a number of research/applied data science efforts have been devoted. To this end, the purpose of this workshop, i.e., the 6th International Workshop on Talent and Management Computing …

Go to article

Akma+: Security And Privacy-Enhanced And Standard-Compatible Akma For 5g Communication, Guomin Yang, Guomin Yang, Yingjiu Li, Minming Huang, Zilin Shen, Imtiaz Karim, Ralf Sasse, David Basin, Elisa Bertino, Jian Weng, Hwee Hwa Pang, Deng, Robert H. Aug 2025

Akma+: Security And Privacy-Enhanced And Standard-Compatible Akma For 5g Communication, Guomin Yang, Guomin Yang, Yingjiu Li, Minming Huang, Zilin Shen, Imtiaz Karim, Ralf Sasse, David Basin, Elisa Bertino, Jian Weng, Hwee Hwa Pang, Deng, Robert H.

Research Collection School Of Computing and Information Systems

The Authentication and Key Management for Applications (AKMA) protocol is a fundamental building block for security and privacy of 5G cellular networks. Therefore, it is critical that the protocol is free of vulnerabilities that can be exploited by attackers. Unfortunately, based on a detailed analysis of AKMA, we show that AKMA has several vulnerabilities that may lead to security and privacy breaches.We define AKMA+, an enhanced protocol for 5G communication that protects against security and privacy breaches while maintaining compatibility with existing standards. AKMA+ includes countermeasures for protecting communication between the user equipment (UE) and application functions (AFs) from attackers, …

Go to article

Faithfulrag: Fact-Level Conflict Modeling For Context-Faithful Retrieval-Augmented Generation, Qinggang Zhang, Zhishang Xiang, Yilin Xiao, Le Wang, Junhui Li, Xinrun Wang, Jinsong Su Aug 2025

Faithfulrag: Fact-Level Conflict Modeling For Context-Faithful Retrieval-Augmented Generation, Qinggang Zhang, Zhishang Xiang, Yilin Xiao, Le Wang, Junhui Li, Xinrun Wang, Jinsong Su

Research Collection School Of Computing and Information Systems

Large language models (LLMs) augmented with retrieval systems have demonstrated significant potential in handling knowledge-intensive tasks. However, these models often struggle with unfaithfulness issues, generating outputs that either ignore the retrieved context or inconsistently blend it with the LLM’s parametric knowledge. This issue is particularly severe in cases of knowledge conflict, where the retrieved context conflicts with the model’s parametric knowledge. While existing faithful RAG approaches enforce strict context adherence through well-designed prompts or modified decoding strategies, our analysis reveals a critical limitation: they achieve faithfulness by forcibly suppressing the model’s parametric knowledge, which undermines the model’s internal knowledge structure …

Go to article

Debate, Reflect, And Distill: Multi-Agent Feedback With Tree-Structured Preference Optimization For Efficient Language Model Enhancement, Xiaofeng Zhou, Heyan Huang, Lizi Liao Aug 2025

Debate, Reflect, And Distill: Multi-Agent Feedback With Tree-Structured Preference Optimization For Efficient Language Model Enhancement, Xiaofeng Zhou, Heyan Huang, Lizi Liao

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks, yet their high computational demands limit widespread adoption. While distilling large models into smaller ones offers a sustainable solution, current techniques—such as static knowledge distillation, resource-intensive reinforcement learning from human feedback, or limited self-reflection—struggle to yield substantial and lasting performance gains. In this paper, we present a novel Debate and Reflect (D&R) framework that orchestrates multi-turn debates between smaller models and stronger teacher models, eliciting actionable feedback (e.g., error analysis, corrective strategies) to guide student models. Further, we introduce Tree-structured Direct Preference Optimization (T-DPO) to …

Go to article

Memotune: A Measure And Moment-Driven Fine-Tuning Framework For Quantized Large Language Models, Yun Zhang, Xue Geng, Lizi Liao, Jintong Sun, Minghe Yu, Ge Yu Aug 2025

Memotune: A Measure And Moment-Driven Fine-Tuning Framework For Quantized Large Language Models, Yun Zhang, Xue Geng, Lizi Liao, Jintong Sun, Minghe Yu, Ge Yu

Research Collection School Of Computing and Information Systems

Quantizing large language models (LLMs) is essential for reducing memory and computational costs in natural language processing. Existing methods combine quantization with parameter-efficient fine-tuning but often fail to meet practical performance requirements. This paper introduces MeMoTune, a novel fine-tuning framework for quantized LLMs. By employing a measure and moment approach within a low-rank approximation framework in probability measure space, MeMoTune optimizes the objective function for superior fine-tuning results. The update process is further refined through scaled gradient, enhancing convergence efficiency and noise robustness. Experiments on tasks like text generation, summarization, and understanding show MeMoTune significantly outperforms state-of-the-art methods, e.g. fine-tuning …

Go to article

R2dqg: A Quality Meets Diversity Framework For Question Generation Over Knowledge Bases, Yimeng Ren, Yanhua Yu, Lizi Liao, Yuhu Shang, Kangkang Lu, Mingliang Yan Aug 2025

R2dqg: A Quality Meets Diversity Framework For Question Generation Over Knowledge Bases, Yimeng Ren, Yanhua Yu, Lizi Liao, Yuhu Shang, Kangkang Lu, Mingliang Yan

Research Collection School Of Computing and Information Systems

The task of Knowledge-Based Question Generation (KBQG) involves generating natural language questions from structured knowledge sources, posing unique challenges in balancing linguistic diversity and semantic relevance. Existing models often focus on maximizing surface-level similarity to ground-truth questions, neglecting the need for diverse syntactic forms and leading to semantic drift during generation. To overcome these challenges, we propose Refine-Reinforced Diverse Question Generation (R2DQG), a two-phase framework leveraging a generation-then-refinement paradigm. The Generator first constructs a diverse set of expressive templates using dependency parse tree similarity, capturing a wide range of syntactic patterns and styles. These templates guide the creation of question …

Go to article

Consistent Client Simulation For Motivational Interviewing-Based Counseling, Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Nicholas Gabriel Lim, Cameron Shi Ern Tan, Phey Ling Kit, Jenny Xiuhui Giam, John Pinto, Ee-Peng Lim Aug 2025

Consistent Client Simulation For Motivational Interviewing-Based Counseling, Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Nicholas Gabriel Lim, Cameron Shi Ern Tan, Phey Ling Kit, Jenny Xiuhui Giam, John Pinto, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Simulating human clients in mental health counseling is crucial for training and evaluating counselors (both human or simulated) in a scalable manner. Nevertheless, past research on client simulation did not focus on complex conversation tasks such as mental health counseling. In these tasks, the challenge is to ensure that the client’s actions (i.e., interactions with the counselor) are consistent with with its stipulated profiles and negative behavior settings. In this paper, we propose a novel framework that supports consistent client simulation for mental health counseling. Our framework tracks the mental state of a simulated client, controls its state transitions, and …

Go to article

Gradients As An Action: Towards Communication-Efficient Federated Recommender Systems Via Adaptive Action Sharing, Zhufeng Lu, Chentao Jia, Ming Hu, Xiaofei Xie, Mingsong Chen Aug 2025

Gradients As An Action: Towards Communication-Efficient Federated Recommender Systems Via Adaptive Action Sharing, Zhufeng Lu, Chentao Jia, Ming Hu, Xiaofei Xie, Mingsong Chen

Research Collection School Of Computing and Information Systems

As a promising privacy-aware collaborative model training paradigm, Federated Learning (FL) is becoming popular in the design of distributed recommender systems. However, Federated Recommender Systems (FedRecs) greatly suffer from two major problems: i) extremely high communication overhead due to massive item embeddings involved in recommendation systems, and ii) intolerably low training efficiency caused by the entanglement of both heterogeneous network environments and client devices. Although existing methods attempt to employ various compression techniques to reduce communication overhead, due to the parameter errors introduced by model compression, they inevitably suffer from model performance degradation. To simultaneously address the above problems, this …

Go to article

Knowledge Boundary Of Large Language Models: A Survey, Moxin Li, Yong Zhao, Wenxuan Zhang, Shuaiyi Li, Wenya Xie, See-Kiong Ng, Tat-Seng Chua, Yang Deng Aug 2025

Knowledge Boundary Of Large Language Models: A Survey, Moxin Li, Yong Zhao, Wenxuan Zhang, Shuaiyi Li, Wenya Xie, See-Kiong Ng, Tat-Seng Chua, Yang Deng

Research Collection School Of Computing and Information Systems

Although large language models (LLMs) store vast amount of knowledge in their parameters, they still have limitations in the memorization and utilization of certain knowledge, leading to undesired behaviors such as generating untruthful and inaccurate responses. This highlights the critical need to understand the knowledge boundary of LLMs, a concept that remains inadequately defined in existing research. In this survey, we propose a comprehensive definition of the LLM knowledge boundary and introduce a formalized taxonomy categorizing knowledge into four distinct types. Using this foundation, we systematically review the field through three key lenses: the motivation for studying LLM knowledge boundaries, …

Go to article

Rl4co: An Extensive Reinforcement Learning For Combinatorial Optimization Benchmark, Federico Berto, Et. Al Aug 2025

Rl4co: An Extensive Reinforcement Learning For Combinatorial Optimization Benchmark, Federico Berto, Et. Al

Research Collection School Of Computing and Information Systems

Combinatorial optimization (CO) is fundamental to several real-world applications, from logistics and scheduling to hardware design and resource allocation. Deep reinforcement learning (RL) has recently shown significant benefits in solving CO problems, reducing reliance on domain expertise and improving computational efficiency. However, the absence of a unified benchmarking framework leads to inconsistent evaluations, limits reproducibility, and increases engineering overhead, raising barriers to adoption for new researchers. To address these challenges, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 27 CO problem environments and 23 state-of-the-art baselines. Built on efficient software libraries and best practices in …

Go to article

Colloquial Singaporean English Style Transfer With Fine-Grained Explainable Control, Jinggui Liang, Dung Vo, Yap Hong Xian, Hai Leong Chieu, Kian Ming A. Chai, Jing Jiang, Lizi Liao Aug 2025

Colloquial Singaporean English Style Transfer With Fine-Grained Explainable Control, Jinggui Liang, Dung Vo, Yap Hong Xian, Hai Leong Chieu, Kian Ming A. Chai, Jing Jiang, Lizi Liao

Research Collection School Of Computing and Information Systems

Colloquial Singaporean English (Singlish) is an informal English marked by a unique blend of languages reflecting Singapore’s multicultural identity. Style transfer between Singlish and Standard (formal) English is vital for various applications, yet existing methods often lack explainability and fine-grained control. To fill this gap, we contribute in two key ways. First, we construct a large, high-quality dataset of formal and informal sentences, annotated across six linguistic aspects—Syntax, Lexical Borrowing, Pragmatics, Prosody/Phonology, Emoticons/Punctuation, and Code-Switching—with detailed explanations. Starting with manually annotated cases, we scaled the dataset to 140K with ensured quality. Second, inspired by the “Society of Mind” theory, we …

Go to article

Gnncontext: Gnn-Based Code Context Prediction For Programming Tasks, Xiaoye Zheng, Zhiyuan Wan, Shun Liu, Kaiwen Yang, David Lo, Xiaohu Yang Aug 2025

Gnncontext: Gnn-Based Code Context Prediction For Programming Tasks, Xiaoye Zheng, Zhiyuan Wan, Shun Liu, Kaiwen Yang, David Lo, Xiaohu Yang

Research Collection School Of Computing and Information Systems

A code context model comprises source code elements and their relations relevant to a programming task. The capture and use of code context models in software tools can benefit software development practices, such as code navigation and search. Prior research has explored approaches that leverage either the structural information of code or interaction histories of developers with integrated development environments to automate the construction of code context models. However, these approaches primarily capture shallow syntactic and lexical features of code elements, with limited ability to capture contextual and structural dependencies among neighboring code elements. In this paper, we propose GNNContext, …

Go to article

Reimagining Education With Ai, Margherita Pagani, Steven M. Miller, Jerry Wind Aug 2025

Reimagining Education With Ai, Margherita Pagani, Steven M. Miller, Jerry Wind

Research Collection School Of Computing and Information Systems

This chapter examines AI’s transformative potential in education, focusing on Generative AI (GenAI) and Large Language Models (LLMs) while at the same time emphasizing the importance of grounding and guiding AI efforts with learning science and education research findings. It synthesizes analyses and expert recommendations, highlighting opportunities like personalized learning and enhanced teacher productivity, alongside challenges such as over-reliance on AI. Practical steps for instructors include adopting a question-first approach, utilizing AI for personalized feedback, designing AI-enhanced learning experiences, fostering critical thinking, and ensuring ethical AI use. The chapter concludes with strategic recommendations for leveraging AI to sustainably improve educational …

Go to article

Learning Frame-Level Classifiers For Video-Based Real-Time Assessment Of Stroke Rehabilitation Exercises From Weakly Annotated Datasets, Ana Rita Cóias, Min Hun Lee, Alexandre Bernardino, Asim Smailagic, Mariana Mateus, David Fernandes, Sofia Trapola Aug 2025

Learning Frame-Level Classifiers For Video-Based Real-Time Assessment Of Stroke Rehabilitation Exercises From Weakly Annotated Datasets, Ana Rita Cóias, Min Hun Lee, Alexandre Bernardino, Asim Smailagic, Mariana Mateus, David Fernandes, Sofia Trapola

Research Collection School Of Computing and Information Systems

Autonomous rehabilitation support solutions, such as virtual coaches, should provide real-time feedback to improve motor function and maintain patient engagement. However, fully annotated dataset collection for real-time exercise assessment is time-consuming and costly, posing a barrier to evaluating proposed methods. In this work, we present a novel framework that learns a frame-level classifier using weakly annotated videos for real-time assessment of compensatory motions in stroke rehabilitation exercises by generating pseudo-labels at a frame level. We consider three approaches: 1) a baseline approach that uses a source dataset to train a frame-level classifier, 2) a transfer learning approach that uses target …

Go to article

Inference-Time Gaze Refinement For Micro-Expression Recognition: Enhancing Event-Based Eye Tracking With Motion-Aware Post-Processing, Panahetipola Mudiyanselage Nuwan Bandara, Thivya Kandappu, Archan Misra Aug 2025

Inference-Time Gaze Refinement For Micro-Expression Recognition: Enhancing Event-Based Eye Tracking With Motion-Aware Post-Processing, Panahetipola Mudiyanselage Nuwan Bandara, Thivya Kandappu, Archan Misra

Research Collection School Of Computing and Information Systems

Event-based eye tracking holds significant promise for fine-grained cognitive state inference, offering high temporal resolution and robustness to motion artifacts, critical features for decoding subtle mental states such as attention, confusion, or fatigue. In this work, we introduce a model-agnostic, inference-time refinement framework designed to enhance the output of existing event-based gaze estimation models without modifying their architecture or requiring retraining. Our method comprises two key post-processing modules: (i) Motion-Aware Median Filtering, which suppresses blink-induced spikes while preserving natural gaze dynamics, and (ii) Optical Flow-Based Local Refinement, which aligns gaze predictions with cumulative event motion to reduce spatial jitter and …

Go to article

First Prev Next Last