Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (9364)
- Computer Sciences (9056)
- Databases and Information Systems (3567)
- Software Engineering (2215)
- Artificial Intelligence and Robotics (1920)
-
- Social and Behavioral Sciences (1630)
- Business (1306)
- Information Security (1112)
- Numerical Analysis and Scientific Computing (1060)
- Graphics and Human Computer Interfaces (952)
- Engineering (935)
- Theory and Algorithms (513)
- Computer Engineering (469)
- Economics (426)
- Operations Research, Systems Engineering and Industrial Engineering (425)
- Programming Languages and Compilers (413)
- Communication (348)
- OS and Networks (346)
- International and Area Studies (336)
- Asian Studies (327)
- Public Affairs, Public Policy and Public Administration (310)
- Education (294)
- Social Media (271)
- Finance and Financial Management (248)
- Environmental Sciences (240)
- Medicine and Health Sciences (228)
- Transportation (220)
- Econometrics (214)
- Technology and Innovation (201)
- Management Information Systems (187)
- Keyword
-
- Machine learning (148)
- Deep learning (130)
- Artificial intelligence (127)
- Singapore (125)
- Social media (82)
-
- Reinforcement learning (74)
- Data mining (70)
- Privacy (67)
- Security (62)
- Sustainability (61)
- Cloud computing (60)
- Deep Learning (58)
- Optimization (56)
- Empirical study (55)
- Software engineering (55)
- Blockchain (52)
- Online learning (52)
- Visualization (52)
- Natural language processing (51)
- Neural networks (50)
- Training (50)
- Anomaly detection (49)
- Large Language Models (49)
- Twitter (49)
- Task analysis (48)
- Collaboration (47)
- Machine Learning (47)
- Feature extraction (45)
- Algorithms (44)
- Semantics (44)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (8567)
- Research Collection Lee Kong Chian School Of Business (428)
- Research Collection School Of Economics (340)
- Dissertations and Theses Collection (Open Access) (272)
- Research Collection School of Social Sciences (193)
-
- Research Collection College of Integrative Studies (138)
- Research Collection Yong Pung How School Of Law (110)
- Research Collection School Of Accountancy (65)
- Asian Management Insights (63)
- Perspectives@SMU (49)
- Dissertations and Theses Collection (20)
- Research Collection Library (19)
- SMU Press Releases and News (18)
- Knowledge@SMU (17)
- FORCE 2026 (14)
- Sim Kee Boon Institute for Financial Economics (14)
- Research@SMU: Connecting the Dots (13)
- Social Space (12)
- MITB Thought Leadership Series (11)
- Research Collection School of Computing and Information Systems (11)
- Oral History Collection (9)
- Report to Stakeholders (9)
- PhD Student’s Publications Collection (8)
- LARC Research Publications (7)
- Research Collection School of Economics (7)
- Student Publications (7)
- Centre for Computational Law (2022-2025) (6)
- CCX Research (5)
- SMU Research Data (4)
- 2024 AI for Research Week (3)
- Publication Type
- File Type
Articles 751 - 780 of 10474
Full-Text Articles in Entire DC Network
Cashift: Benchmarking Log-Based Cloud Attack Detection Under Normality Shift, Jiongchi Yu, Xiaofei Xie, Qiang Hu, Bowen Zhang, Ziming Zhao, Yun Lin, Lei Ma, Ruitao Feng, Frank Liau
Cashift: Benchmarking Log-Based Cloud Attack Detection Under Normality Shift, Jiongchi Yu, Xiaofei Xie, Qiang Hu, Bowen Zhang, Ziming Zhao, Yun Lin, Lei Ma, Ruitao Feng, Frank Liau
Research Collection School Of Computing and Information Systems
With the rapid advancement of cloud-native computing, securing cloud environments has become an important task. Log-based Anomaly Detection (LAD) is the most representative technique used in different systems for attack detection and safety guarantee, where multiple LAD methods and relevant datasets have been proposed. However, even though some of these datasets are specifically prepared for cloud systems, they only cover limited cloud behaviors and lack information from a whole-system perspective. Another critical issue to consider is normality shift, which implies that the test distribution could differ from the training distribution and highly affect the performance of LAD. Unfortunately, existing works …
Regtrieve: Reducing System-Level Regression Errors For Machine Learning Systems Via Retrieval-Enhanced Ensemble, Junming Cao, Xuwen Xiang, Mingfei Cheng, Bihuan Chen, Xinyan Wang, You Lu, Chaofeng Sha, Xiaofei Xie, Xin Peng
Regtrieve: Reducing System-Level Regression Errors For Machine Learning Systems Via Retrieval-Enhanced Ensemble, Junming Cao, Xuwen Xiang, Mingfei Cheng, Bihuan Chen, Xinyan Wang, You Lu, Chaofeng Sha, Xiaofei Xie, Xin Peng
Research Collection School Of Computing and Information Systems
Multiple machine learning (ML) models are often incorporated into real-world ML systems. However, updating an individual model in these ML systems frequently results in regression errors, where the new model performs worse than the old model for some inputs. While model-level regression errors have been widely studied, little is known about how regression errors propagate at system level. To address this gap, we propose RegTrieve, a novel retrieval-enhanced ensemble approach to reduce regression errors at both model and system level. Our evaluation across various model update scenarios shows that RegTrieve reduces system-level regression errors with almost no impact on system …
Unsupervised Recognition Of Unknown Objects For Open-World Object Detection, Ruohuan Fang, Guansong Pang, Wenjun Miao, Xiao Bai, Jin Zheng, Xin Ning
Unsupervised Recognition Of Unknown Objects For Open-World Object Detection, Ruohuan Fang, Guansong Pang, Wenjun Miao, Xiao Bai, Jin Zheng, Xin Ning
Research Collection School Of Computing and Information Systems
Open-world object detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly introduced knowledge. Current OWOD models detect the unknowns that exhibit similar features to the known objects, but they suffer from a severe label bias problem, i.e., they tend to detect all regions (including unknown object regions) that are dissimilar to the known objects as part of the background. To eliminate the label bias, this article proposes a novel module, namely reconstruction error-based Weibull (REW) model, that …
Hvi: A New Color Space For Low-Light Image Enhancement, Qingsen Yan, Yixu Feng, Cheng Zhang, Guansong Pang, Kangbiao Shi, Peng Wu, Wei Dong, Jinqiu Sun, Yanning Zhang
Hvi: A New Color Space For Low-Light Image Enhancement, Qingsen Yan, Yixu Feng, Cheng Zhang, Guansong Pang, Kangbiao Shi, Peng Wu, Wei Dong, Jinqiu Sun, Yanning Zhang
Research Collection School Of Computing and Information Systems
Low-Light Image Enhancement (LLIE) is a crucial computer vision task that aims to restore detailed visual information from corrupted low-light images. Many existing LLIE methods are based on standard RGB (sRGB) space, which often produce color bias and brightness artifacts due to inherent high color sensitivity in sRGB. While converting the images using Hue, Saturation and Value (HSV) color space helps resolve the brightness issue, it introduces significant red and black noise artifacts. To address this issue, we propose a new color space for LLIE, namely Horizontal/Vertical-Intensity (HVI), defined by polarized HS maps and learnable inten sity. The former enforces …
Why Does My Transaction Fail? A First Look At Failed Transactions On The Solana Blockchain, Xiaoye Zheng, Zhiyuan Wan, David Lo, Difan Xie, Xiaohu Yang
Why Does My Transaction Fail? A First Look At Failed Transactions On The Solana Blockchain, Xiaoye Zheng, Zhiyuan Wan, David Lo, Difan Xie, Xiaohu Yang
Research Collection School Of Computing and Information Systems
Solana is an emerging blockchain platform, recognized for its high throughput and low transaction costs, positioning it as a preferred infrastructure for Decentralized Finance (DeFi), Non-Fungible Tokens (NFTs), and other Web 3.0 applications. In the Solana ecosystem, transaction initiators submit various instructions to interact with a diverse range of Solana smart contracts, among which are decentralized exchanges (DEXs) that utilize automated market makers (AMMs), allowing users to trade cryptocurrencies directly on the blockchain without the need for intermediaries. Despite the high throughput and low transaction costs of Solana, the advantages have exposed Solana to bot spamming for financial exploitation, resulting …
Less Is More: On The Importance Of Data Quality For Unit Test Generation, Junwei Zhang, Xing Hu, Shan Gao, Xin Xia, David Lo, Shanping Li
Less Is More: On The Importance Of Data Quality For Unit Test Generation, Junwei Zhang, Xing Hu, Shan Gao, Xin Xia, David Lo, Shanping Li
Research Collection School Of Computing and Information Systems
Unit testing is crucial for software development and maintenance. Effective unit testing ensures and improves software quality, but writing unit tests is time-consuming and labor-intensive. Recent studies have proposed deep learning (DL) techniques or large language models (LLMs) to automate unit test generation. These models are usually trained or fine-tuned on large-scale datasets. Despite growing awareness of the importance of data quality, there has been limited research on the quality of datasets used for test generation. To bridge this gap, we systematically examine the impact of noise on the performance of learning-based test generation models. We first apply the open …
Adapting Large Language Models For Parameter-Efficient Log Anomaly Detection, Ying Fu Lim, Jiawen Zhu, Guansong Pang
Adapting Large Language Models For Parameter-Efficient Log Anomaly Detection, Ying Fu Lim, Jiawen Zhu, Guansong Pang
Research Collection School Of Computing and Information Systems
Log Anomaly Detection (LAD) seeks to identify atypical patterns in log data that are crucial to assessing the security and condition of systems. Although Large Language Models (LLMs) have shown tremendous success in various fields, the use of LLMs in enabling the detection of log anomalies is largely unexplored. This work aims to fill this gap. Due to the prohibitive costs involved in fully fine-tuning LLMs,we explore the use of parameter-efficient fine-tuning techniques (PEFTs) for adapting LLMs to LAD.To have an in-depth exploration of the potential of LLM-driven LAD, we present a comprehensive investigation of leveraging two of the most …
On Sgx’S Voyage To Corporate Sustainability: Exploring Emerging Topics In Multi-Industry Corpora, Xinwen Ni, Min Bin Lin, Simon J.D. Schillebeeckx, Wolfgang Karl Hardle
On Sgx’S Voyage To Corporate Sustainability: Exploring Emerging Topics In Multi-Industry Corpora, Xinwen Ni, Min Bin Lin, Simon J.D. Schillebeeckx, Wolfgang Karl Hardle
Research Collection Lee Kong Chian School Of Business
Topic modeling and LDA (Latent Dirichlet Allocation) have proven valuable in various fields as an innovative approach to studying areas of interest and identifying topics in a dynamic content. The underlying assumption is that techniques like LDA can swiftly capture emerging topics in textual documents compared to other categorization tools. These unsupervised approaches have been used to identify new industries and technological domains. However, our study on the nascent topic of “sustainability” within the corpora of SGX-listed companies highlights clear limitations in employing techniques like LDA on sparse data. The dynamic LDA approach, also called DTM (Dynamic Topic Modelling),based on …
Capacity Investment In The Presence Of Correlated Demand And Production Resource Uncertainties And Its Implications For Financial Hedging, Onur Boyabatli, Guiyun Feng
Capacity Investment In The Presence Of Correlated Demand And Production Resource Uncertainties And Its Implications For Financial Hedging, Onur Boyabatli, Guiyun Feng
Research Collection Lee Kong Chian School Of Business
In manufacturing firms, besides demand uncertainty, capacity investment decisions may also be subject to uncertainty in the availability of a production resource (e.g., budget or commodity component) which may become constraining for manufacturing. When the production resource uncertainty is tied to a financial index (e.g., asset or commodity price), the firm can enter into financial hedging contracts at the time of capacity investment to engineer this uncertainty. Our paper characterizes the optimal capacity investment and hedging decisions and examines how production resource uncertainty impacts the firm’s decisions, profitability, and the value of hedging. We identify three key drivers of these …
Hardiness, Optimism And Hope: Longitudinal Study Of How Individuals May Build Resilience Through Experiential Undergraduate University Courses, Paul Lim, Chin Heng Low, Kevin Koh
Hardiness, Optimism And Hope: Longitudinal Study Of How Individuals May Build Resilience Through Experiential Undergraduate University Courses, Paul Lim, Chin Heng Low, Kevin Koh
Research Collection Lee Kong Chian School Of Business
This study explores the antecedents of students’ resilience in a management education setting, by looking at the role of state hope and dispositional optimism in cultivating their psychological hardiness. While resilience is recognized as integral to personal growth, extant research has predominantly focused on its correlations with psychological capital (PsyCap) elements such as hope and optimism; or examined the outcomes of hardiness as a proxy of resilience. Little has been done to explicate the directional causal relationships among the PsyCap elements and hardiness in view of resilience-building. Using a longitudinal mixed methods design, this study delves into how state hope, …
Lessons Learned From Sandboxing, Piloting And Policy Experimentation With Ai And Other Digital Initiatives: Part 2, Ten In-Depth Interviews, Steven M. Miller
Lessons Learned From Sandboxing, Piloting And Policy Experimentation With Ai And Other Digital Initiatives: Part 2, Ten In-Depth Interviews, Steven M. Miller
Research Collection School Of Computing and Information Systems
This report, "Lessons Learned from Sandboxing, Piloting and Policy Experimentation with AI and Other Digital Initiatives," captures insights and experiences from project experts involved in recent digital innovation initiatives with the governments of Bangladesh, Maldives, and Kazakhstan, and from project experts actively involved with the use of AI for delivering government digital services in the EU, New Zealand, Rwanda, Singapore, United States, and Uzbekistan. The ten in-depth interview write-ups produced from these nine different country settings provide a small but highly informative sample of rich descriptions of some of the important realities, approaches, nuances, issues and challenges related to testing …
Ntire 2025 Challenge On Event-Based Image Deblurring: Methods And Results, Lei Sun, Et. Al.
Ntire 2025 Challenge On Event-Based Image Deblurring: Methods And Results, Lei Sun, Et. Al.
Research Collection School Of Computing and Information Systems
This paper presents an overview of NTIRE 2025, the First Challenge on Event-Based Image Deblurring, detailing the proposed methodologies and corresponding results. The primary goal of the challenge is to design an event-based method that achieves high-quality image deblurring, with performance quantitatively assessed using Peak Signal-toNoise Ratio (PSNR). Notably, there are no restrictions on computational complexity or model size. The task focuses on leveraging both events and images as inputs for singleimage deblurring. A total of 199 participants registered, among whom 15 teams successfully submitted valid results, offering valuable insights into the current state of eventbased image deblurring. We anticipate …
Group-And-Match Vs. Route-Then-Insert: Order Dispatching In Vehicle-Based Dual Services (Vedus), Yue Lin, Hai Yang, Hai Wang
Group-And-Match Vs. Route-Then-Insert: Order Dispatching In Vehicle-Based Dual Services (Vedus), Yue Lin, Hai Yang, Hai Wang
Research Collection School Of Computing and Information Systems
Rapid urban transportation and delivery demand and relevant resource constraints have driven the need for more efficient vehicle utilization. An innovative concept, “Vehicle-based MultiServices” (VeMuS), is a service model in which a single vehicle offers multiple services simultaneously in an urban mobility system. Similarly, “Vehicle-based Dual Services” (VeDuS) refers to a vehicle that provides two services simultaneously (Sun et al., 2023).
Potential And Pitfalls Of Romantic Artificial Intelligence (Ai) Companions: A Systematic Review, Qi Hui Jerlyn Ho, Meilan Hu, Tracy Xi Chen, Andree Hartanto
Potential And Pitfalls Of Romantic Artificial Intelligence (Ai) Companions: A Systematic Review, Qi Hui Jerlyn Ho, Meilan Hu, Tracy Xi Chen, Andree Hartanto
Research Collection School of Social Sciences
As Artificial Intelligence (AI) becomes more integrated into daily life, individuals have increasingly turned to AIdriven systems for emotional support, companionship, and even romantic relationships. These relationships can be both beneficial and detrimental. Given the need for a comprehensive understanding of this phenomenon, this systematic review uses Sternberg’s Triangular Theory of Love to provide a holistic summary of its key potentials and pitfalls. A total of 23 articles were identified from the following databases: EBSCOhost ERIC, EBSCOhost PsycInfo, PubMed, Scopus, and Web of Science. Results highlighted the key potentials of being in a romantic relationship with AI companions as: the …
On-Demand Heterogeneous Drone Delivery Problem, Xupeng Wen, Zhiguang Cao, Shu Xu, Dapeng Ren, Guohua Wu, Yaoxin Wu
On-Demand Heterogeneous Drone Delivery Problem, Xupeng Wen, Zhiguang Cao, Shu Xu, Dapeng Ren, Guohua Wu, Yaoxin Wu
Research Collection School Of Computing and Information Systems
In the on-demand problem domain, actual demand frequently deviates from the expected demand. This paper intricately delves into the exploration of on-demand heterogeneous multi-drone routing problem (ODHDRP), in which a transport drone carries multiple terminal drones to subregions in the first echelon, and the terminal drones deliver parcels during a flight trip to customers with demands in subregions to maintain economies of scale in the second echelon. We formulate the customer demands using a normal distribution, and exploit a reliability model of customer demands with chance constraints. To solve the ODHDRP efficiently, we propose a hybrid iterative optimisation heuristic (HIOH) …
Moditector: Module-Directed Testing For Autonomous Driving Systems, Renzhi Wang, Mingfei Cheng, Xiaofei Xie, Yuan Zhou, Lei Ma
Moditector: Module-Directed Testing For Autonomous Driving Systems, Renzhi Wang, Mingfei Cheng, Xiaofei Xie, Yuan Zhou, Lei Ma
Research Collection School Of Computing and Information Systems
Testing Autonomous Driving Systems (ADSs) is crucial for ensuring their safety, reliability, and performance. Despite numerous testing methods available that can generate diverse and challenging scenarios to uncover potential vulnerabilities, these methods often treat ADS as a black-box, primarily focusing on identifying system-level failures like collisions or near-misses without pinpointing the specific modules responsible for these failures. This lack of root causes understanding for the failures hinders effective debugging and subsequent system repair. Furthermore, current approaches often fall short in generating violations that adequately test the individual modules of an ADS from a system-level perspective, such as perception, prediction, planning, …
Demystifying Memorization In Llm-Based Program Repair Via A General Hypothesis Testing Framework, Jiaolong Kong, Xiaofei Xie, Shangqing Liu
Demystifying Memorization In Llm-Based Program Repair Via A General Hypothesis Testing Framework, Jiaolong Kong, Xiaofei Xie, Shangqing Liu
Research Collection School Of Computing and Information Systems
Large Language Models (LLMs) have achieved remarkable success in various applications, particularly in code-related tasks such as code generation and program repair, setting new performance benchmarks. However, the extensive use of large training corpora raises concerns about whether these achievements stem from genuine understanding or mere memorization of training data—a question often overlooked in current research. This paper aims to study the memorization issue within LLM-based program repair by investigating whether the correct patches generated by LLMs are the result of memorization. The key challenge lies in the absence of ground truth for confirming memorization, leading to various ad-hoc methods …
Collaborative Tree Search For Enhancing Embodied Multi-Agent Collaboration, Lizheng Zu, Lin Lin, Song Fu, Na Zhao, Pan Zhou
Collaborative Tree Search For Enhancing Embodied Multi-Agent Collaboration, Lizheng Zu, Lin Lin, Song Fu, Na Zhao, Pan Zhou
Research Collection School Of Computing and Information Systems
Embodied agents based on large language models (LLMs) face significant challenges in collaborative tasks, requiring effective communication and reasonable division of labor to ensure efficient and correct task completion. Previous approaches with simple communication patterns carry erroneous or incoherent agent actions, which can lead to additional risks. To address these problems, we propose Cooperative Tree Search (CoTS), a framework designed to significantly improve collaborative planning and task execution efficiency among embodied agents. CoTS guides multi-agents to discuss long-term strategic plans within a modified Monte Carlo tree, searching along LLMdriven reward functions to provide a more thoughtful and promising approach to …
Modfinity: Unsupervised Domain Adaptation With Multimodal Information Flow Intertwining, Shanglin Liu, Jianming Lv, Jingdan Kang, Huaidong Zhang, Zequan Liang, Shengfeng He
Modfinity: Unsupervised Domain Adaptation With Multimodal Information Flow Intertwining, Shanglin Liu, Jianming Lv, Jingdan Kang, Huaidong Zhang, Zequan Liang, Shengfeng He
Research Collection School Of Computing and Information Systems
Multimodal unsupervised domain adaptation leverages unlabeled data in the target domain to enhance multimodal systems continuously. While current state-of-the-art methods encourage interaction between sub-models of different modalities through pseudo-labeling and feature-level exchange, varying sample quality across modalities can lead to the propagation of inaccurate information, resulting in error accumulation. To address this, we propose Modal-Affinity Multimodal Domain Adaptation (MODfinity), a method that dynamically manages multimodal information flow through fine-grained control over teacher model selection, guiding information intertwining at both feature and label levels. By treating labels as an independent modality, MODfinity enables balanced performance assessment across modalities, employing a novel …
A Knowledge Enhanced Large Language Model For Bug Localization, Yue Li, Bohan Liu, Ting Zhang, Zhiqi Wang, David Lo, Lanxin Yang, Jun Lyu, He Zhang
A Knowledge Enhanced Large Language Model For Bug Localization, Yue Li, Bohan Liu, Ting Zhang, Zhiqi Wang, David Lo, Lanxin Yang, Jun Lyu, He Zhang
Research Collection School Of Computing and Information Systems
A significant number of bug reports are generated every day as software systems continue to develop. Large Language Models (LLMs) have been used to correlate bug reports with source code to locate bugs automatically. The existing research has shown that LLMs are effective for bug localization and can increase software development efficiency. However, these studies still have two limitations. First, these models fail to capture context information about bug reports and source code. Second, these models are unable to understand the domain-specific expertise inherent to particular projects, such as version information in projects that are composed of alphanumeric characters without …
Efficient And Green Large Language Models For Software Engineering: Literature Review, Vision, And The Road Ahead, Jieke Shi, Zhou Yang, David Lo
Efficient And Green Large Language Models For Software Engineering: Literature Review, Vision, And The Road Ahead, Jieke Shi, Zhou Yang, David Lo
Research Collection School Of Computing and Information Systems
Large Language Models (LLMs) have recently shown remarkable capabilities in various software engineering tasks, spurring the rapid growth of the Large Language Models for Software Engineering (LLM4SE) area. However, limited attention has been paid to developing efficient LLM4SE techniques that demand minimal computational cost, time, and memory resources, as well as green LLM4SE solutions that reduce energy consumption, water usage, and carbon emissions. This article aims to redirect the focus of the research community toward the efficiency and greenness of LLM4SE, while also sharing potential research directions to achieve this goal. It commences with a brief overview of the significance …
Deepvec: State-Vector Aware Test Case Selection For Enhancing Recurrent Neural Network, Zhonghao Jiang, Meng Yan, Li Huang, Weifeng Sun, Chao Liu, Song Sun, David Lo
Deepvec: State-Vector Aware Test Case Selection For Enhancing Recurrent Neural Network, Zhonghao Jiang, Meng Yan, Li Huang, Weifeng Sun, Chao Liu, Song Sun, David Lo
Research Collection School Of Computing and Information Systems
Deep Neural Networks (DNN) have realized significant achievements across various application domains. There is no doubt that testing and enhancing a pre-trained DNN that has been deployed in an application scenario is crucial, because it can reduce the failures of the DNN. DNN-driven software testing and enhancement require large amounts of labeled data. The high cost and inefficiency caused by the large volume of data of manual labeling, and the time consumption of testing all cases in real scenarios are unacceptable. Therefore, test case selection technologies are proposed to reduce the time cost by selecting and only labeling representative test …
Building Narratives And Probing Concepts: Preparing Materials For Co-Design With Autistic Livestreamers, Terrance Mok, Tyson Hartley, Anthony Tang, Adam Mccrimmon, Lora Oehlberg
Building Narratives And Probing Concepts: Preparing Materials For Co-Design With Autistic Livestreamers, Terrance Mok, Tyson Hartley, Anthony Tang, Adam Mccrimmon, Lora Oehlberg
Research Collection School Of Computing and Information Systems
Based on ten semi-structured interviews with autistic Twitch streamers, we introduce a series of scenario-based design narratives coupled with technology design concepts as a starting point for co-design discussion about autistic streaming. This work builds on prior thematic analysis of the unique intersection between autism and livestreaming. Our user-centered scenarios highlight the needs, goals, and challenges of autistic individuals in livestreaming contexts. By using evocative narratives, the scenarios serve to facilitate empathy and deeper engagement with the needs of autistic users, and help facilitate and support co-creative dialogues and discussions about new technology designs. We contribute this starting point for …
Meta-Learning Hyperparameters For Foundation Model Adaptation In Remote-Sensing Imagery, Zichen Tian, Yaoyao Liu, Qianru Sun
Meta-Learning Hyperparameters For Foundation Model Adaptation In Remote-Sensing Imagery, Zichen Tian, Yaoyao Liu, Qianru Sun
Research Collection School Of Computing and Information Systems
Training large foundation models of remote-sensing (RS) images is almost impossible due to the limited and long-tailed data problems. Fine-tuning natural image pre-trained models on RS images is a straightforward solution. To reduce computational costs and improve performance on tail classes, existing methods apply parameter-efficient fine-tuning (PEFT) techniques, such as LoRA and AdaptFormer. However, we observe that fixed hyperparameters -- such as intra-layer positions, layer depth, and scaling factors, can considerably hinder PEFT performance, as fine-tuning on RS images proves highly sensitive to these settings. To address this, we propose MetaPEFT, a method incorporating adaptive scalers that dynamically adjust module …
Chatgpt’S Performance Evaluation In Spreadsheets Modeling To Inform Assessments Redesign, Michelle L. F. Cheong
Chatgpt’S Performance Evaluation In Spreadsheets Modeling To Inform Assessments Redesign, Michelle L. F. Cheong
Research Collection School Of Computing and Information Systems
Background: Increasingly, students are using ChatGPT to assist them in learning and even completing their assessments, raising concerns of academic integrity and loss of critical thinking skills. Many articles suggested educators to redesign assessments which are more “Generative-AI-resistant” and to focus on assessing students on higher order thinking skills. However, there is a lack of articles that attempt to quantify assessments at different cognitive levels to provide empirical study insights on ChatGPT’s performance at different levels, which will affect how educators redesign their assessments.Objectives: Educators need new information on how well ChatGPT performs to redesign future assessments to assess their …
Outperforming The Best With Minimal Effort: Algorithm Selection For Constrained Multi-Objective Optimization, Mustafa Misir, Aldy Gunawan
Outperforming The Best With Minimal Effort: Algorithm Selection For Constrained Multi-Objective Optimization, Mustafa Misir, Aldy Gunawan
Research Collection School Of Computing and Information Systems
The present study performs algorithm selection on a suite of optimization algorithms targeting the constrained multi-objective optimization problems. The idea is to utilize the existing, relevant algorithmic experience in the literature to deliver an improved solver with limited effort. The reason being that algorithm development, in general, is a challenging and time-consuming process, especially with the goal of outperforming the existing methods from varying perspectives such as performance, speed, and robustness. Concerning the multi-objective optimization problems, the required development efforts happen to be even harder than addressing the single-objective ones. Furthermore, referring to the fact that the number of candidate …
Alayadb: The Data Foundation For Efficient And Effective Long-Context Llm Inference, Yangshen Deng, Zhengxin You, Long Xiang, Qilong Li, Peiqi Yuan, Zhaoyang Hong, Yitao Zheng, Wanting Li, Runzhong Li, Haotian Liu, Kyriakos Mouratidis, Man Lung Yiu, Huan Li, Qiaomu Shen, Rui Mao, Bo Tang
Alayadb: The Data Foundation For Efficient And Effective Long-Context Llm Inference, Yangshen Deng, Zhengxin You, Long Xiang, Qilong Li, Peiqi Yuan, Zhaoyang Hong, Yitao Zheng, Wanting Li, Runzhong Li, Haotian Liu, Kyriakos Mouratidis, Man Lung Yiu, Huan Li, Qiaomu Shen, Rui Mao, Bo Tang
Research Collection School Of Computing and Information Systems
AlayaDB is a cutting-edge vector database system natively architected for efficient and effective long-context inference for Large Language Models (LLMs) at AlayaDB AI. Specifically, it decouples the KV cache and attention computation from the LLM inference systems, and encapsulates them into a novel vector database system. For the Model as a Service providers (MaaS), AlayaDB consumes fewer hardware resources and offers higher generation quality for various workloads with different kinds of Service Level Objectives (SLOs), when compared with the existing alternative solutions (e.g., KV cache disaggregation, retrieval-based sparse attention). The crux of AlayaDB is that it abstracts the attention computation …
Reaccept: Automated Co-Evolution Of Production And Test Code Based On Dynamic Validation And Large Language Models, Jianlei Chi, Xiaotian Wang, Yuhan Huang, Lechen Yu, Di Cui, Jianguo Sun, Jun Sun
Reaccept: Automated Co-Evolution Of Production And Test Code Based On Dynamic Validation And Large Language Models, Jianlei Chi, Xiaotian Wang, Yuhan Huang, Lechen Yu, Di Cui, Jianguo Sun, Jun Sun
Research Collection School Of Computing and Information Systems
Synchronizing production and test code, known as PT co-evolution, is critical for software quality. Given the significant manual effort involved, researchers have tried automating PT co-evolution using predefined heuristics and machine learning models. However, existing solutions are still incomplete. Most approaches only detect and flag obsolete test cases, leaving developers to manually update them. Meanwhile, existing solutions may suffer from low accuracy, especially when applied to real-world software projects. In this paper, we propose ReAccept, a novel approach leveraging large language models (LLMs), retrievalaugmented generation (RAG), and dynamic validation to fully automate PT co-evolution with high accuracy. ReAccept employs an …
De-Duplicating Silent Compiler Bugs Via Deep Semantic Representation, Junjie Chen, Xingyu Fan, Chen Yang, Shuang Liu, Jun Sun
De-Duplicating Silent Compiler Bugs Via Deep Semantic Representation, Junjie Chen, Xingyu Fan, Chen Yang, Shuang Liu, Jun Sun
Research Collection School Of Computing and Information Systems
The compiler bug duplication problem (where many test failures are caused by the same compiler bug) can lead to huge waste of time and resource in diagnosing test failures produced by compiler testing. It is particularly challenging with regard to the silent compiler bugs that do not produce any error messages. To address this problem, multiple white-box techniques were proposed, but they are inapplicable in many practical scenarios. Black-box techniques are more practical, but the existing ones are less effective as they often rely on irrelevant syntactic information. To bridge this gap, we propose a novel black-box technique (BLADE), which …
A Comprehensive Study Of Oop-Related Bugs In C++ Compilers, Bo Wang, Chong Chen, Junjie Chen, Bowen Xu, Chen Ye, Youfang Lin, Guoliang Dong, Jun Sun
A Comprehensive Study Of Oop-Related Bugs In C++ Compilers, Bo Wang, Chong Chen, Junjie Chen, Bowen Xu, Chen Ye, Youfang Lin, Guoliang Dong, Jun Sun
Research Collection School Of Computing and Information Systems
Modern C++, a programming language characterized by its extensive use of object-oriented programming (OOP) features, is widely used for system programming. However, C++ compilers often struggle to correctly handle these sophisticated OOP features, resulting in numerous high-profile compiler bugs that can lead to crashes or miscompilation. Despite the significance of OOP-related bugs, existing studies largely overlook OOP features, hindering their ability to discover such bugs. To assist both compiler fuzzer designers and compiler developers, we conduct a comprehensive study of the compiler bugs caused by incorrectly handling C++ OOP-related features. First, we systematically extract 788 OOP-related C++ compiler bugs from …