Open Access. Powered by Scholars. Published by Universities.®
Artificial Intelligence and Robotics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Databases and Information Systems (360)
- Engineering (296)
- Operations Research, Systems Engineering and Industrial Engineering (256)
- Business (177)
- Graphics and Human Computer Interfaces (176)
-
- Social and Behavioral Sciences (173)
- Software Engineering (137)
- Numerical Analysis and Scientific Computing (112)
- Theory and Algorithms (103)
- Public Affairs, Public Policy and Public Administration (75)
- Transportation (63)
- Programming Languages and Compilers (62)
- Information Security (43)
- Medicine and Health Sciences (43)
- Technology and Innovation (38)
- OS and Networks (37)
- Education (36)
- Law (36)
- Asian Studies (35)
- Computer Engineering (35)
- International and Area Studies (35)
- Health Information Technology (30)
- Science and Technology Law (22)
- Psychology (21)
- Library and Information Science (20)
- Finance and Financial Management (18)
- Higher Education (18)
- Keyword
-
- Artificial intelligence (98)
- Machine learning (55)
- Reinforcement learning (42)
- Deep learning (38)
- Artificial Intelligence (30)
-
- Large Language Models (30)
- Generative AI (29)
- ChatGPT (23)
- Large Language Model (23)
- Large language models (23)
- Singapore (22)
- Computer vision (19)
- Large language model (18)
- Optimization (18)
- Reinforcement Learning (18)
- Scheduling (18)
- Anomaly detection (17)
- Natural language processing (17)
- Deep reinforcement learning (16)
- Deep Learning (15)
- LLMs (15)
- Machine Learning (15)
- Vehicle routing problem (15)
- AI (14)
- Neural networks (13)
- Uncertainty (13)
- Software engineering (12)
- Graph neural networks (11)
- Metaverse (10)
- Multi-agent systems (10)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (1664)
- Dissertations and Theses Collection (Open Access) (57)
- Research Collection Lee Kong Chian School Of Business (33)
- Research Collection Yong Pung How School Of Law (31)
- Research Collection School of Social Sciences (22)
-
- Asian Management Insights (16)
- FORCE 2026 (14)
- Perspectives@SMU (11)
- Research Collection College of Integrative Studies (10)
- Research Collection Library (8)
- PhD Student’s Publications Collection (6)
- MITB Thought Leadership Series (4)
- 2024 AI for Research Week (3)
- CCX Research (3)
- LARC Research Publications (2)
- Research Collection School Of Accountancy (2)
- CASTLe: Collection of Articles on Scholarship for Teaching and Learning (1)
- Centre for AI & Data Governance (2019-2025) (1)
- Centre for Computational Law (2022-2025) (1)
- ROSA Journal Articles and Publications (1)
- Research Collection Office of Research (1)
- Research Collection School Of Economics (1)
- Research@SMU Infographics (1)
- Research@SMU: Connecting the Dots (1)
- SMU Press Releases and News (1)
- Sim Kee Boon Institute for Financial Economics (1)
- Student Publications (1)
- Publication Type
- File Type
Articles 61 - 90 of 1897
Full-Text Articles in Artificial Intelligence and Robotics
[Birds-Of-A-Feather] Understanding And Handling Software Plagiarism In The Age Of Generative Ai, Daniel S. Katz, Scott C. Edmunds
[Birds-Of-A-Feather] Understanding And Handling Software Plagiarism In The Age Of Generative Ai, Daniel S. Katz, Scott C. Edmunds
FORCE 2026
Computing and software have supported research since their inception, and continue to play a significant role in knowledge production. However, the means of communicating research methods and results were developed long before computing existed, and the research community lacks best practices for documenting computational research elements transparently, reproducibly, and reusably.
Publishers are now more accepting of the inclusion of software (typically, source code) associated with submitted manuscripts, and many want to support processes to vouch for the integrity of software just as they do for other content, such as ensuring that ethical and legal concerns such as authorship, plagiarism, copyrights …
Diamond Open Access Journals In India: Status, Sustainability And Challenges, Mallikarjun Dora, Kanagasabai K, Raj Kishor Kampa
Diamond Open Access Journals In India: Status, Sustainability And Challenges, Mallikarjun Dora, Kanagasabai K, Raj Kishor Kampa
FORCE 2026
Open-access publishing has transformed scholarly communication in recent decades. The share of OA articles between 2014 and 2024 increased by 26%, from a modest 14% in 2014 to 40% in 2024. OA journals have evolved over time and exist in various models based on funding mechanisms, including the Gold, Green, Hybrid, and Diamond models. While OA publishing emerged in response to scientific inequality, middle- and low-income countries face the barrier of high Article Processing Charges (APC), which hinder them from publishing in those journals (Alperin, 2022). The Article Processing Charges are part of the Gold and Hybrid OA models, where …
Can Ai Help In Systematic Reviews? A Comparative Study Of Manual, Ai-Assisted, And Ai-Dominant Workflows For Librarians And Researchers, Aster Zhao
FORCE 2026
Systematic reviews are essential to evidence-based research but are often time-consuming and labor-intensive, for researchers to conduct, and for librarians to participate in, or teach. The rapid advances in Generative AI and AI-powered research tools, have created a growing interest in whether these technologies can assist—or even automate—parts of the systematic review process. However, questions remain about their effectiveness, reproducibility, and potential bias. This study explores the role of GenAI tools in the early stages of a systematic review: from literature discovery and screening, up to the identification of included studies.
We propose a comparative case study of one systematic …
Genai In Qualitative Data Analysis: Framework-Guided Prompt Engineering In Library Research Practice, Debby R. Wegener
Genai In Qualitative Data Analysis: Framework-Guided Prompt Engineering In Library Research Practice, Debby R. Wegener
FORCE 2026
As Generative AI (GenAI) tools become increasingly integrated across the research lifecycle, researchers need practical, reproducible methods for the responsible use of these technologies. This presentation will demonstrate a systematic approach to using GenAI for qualitative data analysis through a case study of thematic coding in a library website usability study at the Singapore Institute of Technology.
Drawing on prompt engineering frameworks like CLEAR, this session will illustrate how structured prompts can maintain academic rigour and enhance the reliability of GenAI-assisted analysis. The presentation will walk through the complete workflow, that is, from initial data preparation and tool selection to …
Using Ai-Assisted Programming To Develop Research Services Tools For Research Impact, Open Access Publishing & More, Gary Lee
FORCE 2026
Academic libraries play a vital role in scholarly communication, As research practices become more data‑driven and interdisciplinary, librarians can help scholars by creating and sharing flexible, customizable tools that align with local workflows and user needs.
AI Assisted programming (sometimes called “vibe coding”) offers a new way for librarians without extensive programming knowledge to develop such tools . This allows previously non-expert librarians to go from conceptual goals to working applications by rapid prototyping, experimentation, and roll-out, resulting in service innovation and improvement.
This presentation illustrates how librarians at HKUST have explored vibe coding with tools like GROK, POE, and …
Recognizing And Rewarding Peer Review: Rethinking Research Assessment For Openness, Fairness, And Global Equity, Tung Tung Chan, Bernd Pulverer, Johan Rooryck
Recognizing And Rewarding Peer Review: Rethinking Research Assessment For Openness, Fairness, And Global Equity, Tung Tung Chan, Bernd Pulverer, Johan Rooryck
FORCE 2026
The Coalition for Advancing Research Assessment (CoARA) Working Group on Recognizing and Rewarding Peer Review has developed a comprehensive framework for reforming how scholarly review is valued within research careers. Our recommendations address a fundamental question: how can peer review, a critical yet often invisible scholarly contribution, be made visible, credited, and meaningfully integrated into research assessment?
Developed through a collaborative effort across 16 European organisations, the Working Group’s outputs offer targeted recommendations for four key stakeholder groups: research performing organizations, research funding bodies, publishers and editors, and individual researchers. These recommendations are structured across five key dimensions:
(1) Openness: …
Open Research Information - How To Support Publishers To Make Metadata Openly Availble, Bianca Kramer
Open Research Information - How To Support Publishers To Make Metadata Openly Availble, Bianca Kramer
FORCE 2026
Research information, or scholarly metadata, is important for decision making around strategic priorities, distribution of resources, and evaluation of researchers and institutions. It is also used to assess the effect of policies, and to find and assess research results. Open research information (free to access and free to (re)use) is increasingly valued for fair assessment and equitable decision making, and is also important in digital sovereignty.
The Barcelona Declaration on Open Research Information calls on organizations performing, funding and evaluating research to make openness of research information the default, work with services and systems that support and enable open research …
Emotional Support Through Ai: Venting To Artificial Intelligence Or A Perceived Human May Offer Comparable Emotional Well-Being Benefits, Meilan Hu, Jerlyn Q. H. Ho, Claire Ng, Shermaine S. M. Wong, Andree Hartanto
Emotional Support Through Ai: Venting To Artificial Intelligence Or A Perceived Human May Offer Comparable Emotional Well-Being Benefits, Meilan Hu, Jerlyn Q. H. Ho, Claire Ng, Shermaine S. M. Wong, Andree Hartanto
Research Collection School of Social Sciences
Artificial Intelligence (AI) chatbots are increasingly being explored as sources of informal emotional support, with emerging evidence suggesting that venting to these systems can reduce negative affect. Yet, it remains unclear whether such benefits depend on the responder's perceived identity. Given that emotional relief from venting often hinges on perceived authenticity and emotional validation, this study investigates whether the emotional well-being benefits of venting differ when users believe they are interacting with an AI chatbot versus a human, even when responses are content-matched. In a pre-registered experiment ( N = 279), participants were randomly assigned to either an AI-assisted venting …
Towards Efficient Continual Learning: From Memory Optimization To Foundation Models, Zilin Luo
Towards Efficient Continual Learning: From Memory Optimization To Foundation Models, Zilin Luo
Dissertations and Theses Collection (Open Access)
Continual learning, also termed lifelong learning, enables machine learning models to incrementally acquire new knowledge while mitigating the degradation of previously learned information—a capability essential for adapting to dynamic, real-world data environments. This dissertation investigates the core challenges of continual learning and extends its application to enhancing training efficiency in the era of foundation models. The first part of this dissertation addresses the constraints of few-shot exemplar storage with a novel compression framework. While leveraging class activation maps to downsample non-discriminative pixels, we introduce an adaptive masking model, optimized through bilevel optimization, to store more exemplars efficiently. The second part …
Towards Auto-Evaluation For Large Language Models, Jiahao Ying
Towards Auto-Evaluation For Large Language Models, Jiahao Ying
Dissertations and Theses Collection (Open Access)
The rapid advancement of large language models (LLMs) has created an urgent need for evaluation methodologies that are timely, scalable, reliable, and informative. Conventional evaluation benchmarks, although essential for measuring model capabilities and guiding model development, are often constructed and maintained through labor-intensive human annotation. As LLMs continue to improve through increases in model scale, training data, and computational resources, static benchmarks may quickly lose discriminative power. Moreover, the growing use of large and diverse training corpora increases the risk of benchmark leakage, which can inflate evaluation results and obscure the true capabilities of models. These challenges call for a …
Ai In Healthcare: Regulatory Guidelines And Judge-Made Negligence Principles For Ai Implementers, Gary K. Y. Chan
Ai In Healthcare: Regulatory Guidelines And Judge-Made Negligence Principles For Ai Implementers, Gary K. Y. Chan
Research Collection Yong Pung How School Of Law
The use of artificial intelligence (AI) in healthcare may, notwithstanding its potential benefits, result in harm to patients from allegedly negligent acts or omissions by hospitals and medical doctors. In such circumstances, how should the principles in the tort of negligence (duty of care, breach, causation, remoteness of damage, and defences) respond to AI innovations in healthcare? In particular, how may the standard of care expected of hospitals and medical doctors be informed by regulatory guidelines? We refer to case law precedents and regulatory guidelines on the roles and responsibilities of doctors and hospitals as AI implementers. Importantly, they prompt …
How To Save The Take-Home Essay With Oral Assessments, Matthew Hammerton, Jacqueline Ho
How To Save The Take-Home Essay With Oral Assessments, Matthew Hammerton, Jacqueline Ho
Research Collection School of Social Sciences
In a commentary, the authors opined that pairing take-home essays with oral assessments is a more effective response to AI than policing its use. Students who cannot adequately explain their work can be marked down, reducing incentives to rely on AI. They noted that oral exams help preserve key elements of university education – intellectual effort, ownership, and human relationships – while allowing take-home essays to remain relevant in an AI-driven landscape that demands greater emphasis on understanding, responsibility, and dialogue.
Scaling Up Multi-Agent Reinforcement Learning For Large Agent Teams And Long-Horizon Tasks: A Survey, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan
Scaling Up Multi-Agent Reinforcement Learning For Large Agent Teams And Long-Horizon Tasks: A Survey, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
Multi-agent reinforcement learning (MARL) empowers multiple autonomous agents to acquire effective policies for collaborative problem-solving. Over the last decade, MARL has seen significant advancements, with numerous algorithms achieving impressive performance across various benchmarks and real-world applications. Nevertheless, the scalability of multi-agent systems, in terms of the number of agents and the length of the task horizon, remains a critical consideration for applying MARL methods to complex problem-solving. Given that a dedicated review of the existing approaches and challenges in scaling up multi-agent systems remains largely absent, this survey aims to bridge this gap by delivering a comprehensive review of MARL …
Rode: Linear Rectified Mixture Of Diverse Experts For Food Large Multi-Modal Models, Pengkun Jiao, Xinlan Wu, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yu-Gang
Rode: Linear Rectified Mixture Of Diverse Experts For Food Large Multi-Modal Models, Pengkun Jiao, Xinlan Wu, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yu-Gang
Research Collection School Of Computing and Information Systems
Large Multi-modal Models (LMMs) have significantly advanced a variety of vision-language tasks. The scalability and availability of high-quality training data play a pivotal role in the success of LMMs. In the realm of food, while comprehensive food datasets such as Recipe1M offer an abundance of ingredient and recipe information, they often fall short of providing ample data for nutritional analysis. The Recipe1M+ dataset, despite offering a subset for nutritional evaluation, is limited in the scale and accuracy of nutrition information. To bridge this gap, we introduce Uni-Food, a unified food dataset that comprises over 100,000 images with various food labels, …
Benchmarking Gaslighting Negation Attacks Against Multimodal Large Language Models, Bin Zhu, Yinxuan Gui, Huiyan Qi, Jingjing Chen, Chong-Wah Ngo, Ee-Peng Lim
Benchmarking Gaslighting Negation Attacks Against Multimodal Large Language Models, Bin Zhu, Yinxuan Gui, Huiyan Qi, Jingjing Chen, Chong-Wah Ngo, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
Multimodal Large Language Models (MLLMs) have exhibited remarkable advancements in integrating different modalities, excelling in complex understanding and generation tasks. Despite their success, MLLMs remain vulnerable to conversational adversarial inputs. In this paper, we systematically study gaslighting negation attacks—a phenomenon where models, despite initially providing correct answers, are persuaded by user-provided negations to reverse their outputs, often fabricating justifications. We conduct extensive evaluations of state-of-the-art MLLMs across diverse benchmarks and observe substantial performance drops when negation is introduced. Notably, we introduce the first benchmark GaslightingBench, specifically designed to evaluate the vulnerability of MLLMs to negation arguments. GaslightingBench consists of multiple-choice …
Videocreator: An Agentic System For Multi-Turn Video Production, Zhengyang Liang, Yan Shu, Cathal Gurrin, Nicu Sebe, Lizi Liao
Videocreator: An Agentic System For Multi-Turn Video Production, Zhengyang Liang, Yan Shu, Cathal Gurrin, Nicu Sebe, Lizi Liao
Research Collection School Of Computing and Information Systems
Recent advances in video generation models enable visually compelling single clips. However, real-world video creation is inherently continuous and iterative: creators refine content over multiple rounds while maintaining narrative, style, and entity consistency. Existing standalone generators are largely stateless and lack memory of previously generated segments, making it difficult to produce a coherent and consistent video project. To address this gap, we present VideoCreator, a unified video agent that integrates generation and understanding with a project-level memory system. VideoCreator leverages understanding capabilities to perform fine-grained analysis of newly produced content and uses persistent memory to retain and reuse prior context …
Interfold: Learning Interpretable Diffusion Manifolds Beyond Binary Samples, Alexander Vincent Lewi, Rainer Tan, Shengfeng He
Interfold: Learning Interpretable Diffusion Manifolds Beyond Binary Samples, Alexander Vincent Lewi, Rainer Tan, Shengfeng He
Research Collection School Of Computing and Information Systems
We propose InterFold, a framework for learning and applying interpretable semantic manifolds in latent diffusion models, without requiring binary or paired supervision. Existing methods for semantic editing either rely on limited paired data or uncover only coarse, unsupervised directions that fail to capture user-specific, fine-grained attributes. InterFold addresses these limitations by learning a target attribute manifold in the H-space of diffusion models using only a set of positive, unlabeled examples. To edit a new image, InterFold projects its H-space representation toward this learned manifold through test-time optimization, enabling precise, identity-preserving modifications of complex, non-binary concepts. To make these edits effective …
Sam3-Litetext: An Anatomical Study Of The Sam3 Text Encoder For Efficient Vision-Language Segmentation, Chengxi Zeng, Yuxuan Jiang, Ge Gao, Shuai Wang, Duolikun Danier, Bin Zhu, Stevan Rudinac, David Bull, Fan Zhang
Sam3-Litetext: An Anatomical Study Of The Sam3 Text Encoder For Efficient Vision-Language Segmentation, Chengxi Zeng, Yuxuan Jiang, Ge Gao, Shuai Wang, Duolikun Danier, Bin Zhu, Stevan Rudinac, David Bull, Fan Zhang
Research Collection School Of Computing and Information Systems
Vision-language segmentation models such as SAM3 enable flexible, prompt-driven visual grounding, but inherit large, general-purpose text encoders originally designed for open-ended language understanding. In practice, segmentation prompts are short, structured, and semantically constrained, leading to substantial over-provisioning in text encoder capacity and persistent computational and memory overhead. In this paper, we perform a large-scale anatomical analysis of text prompting in vision–language segmentation, covering 404,796 real prompts across multiple benchmarks. Our analysis reveals severe redundancy: most context windows are underutilized, vocabulary usage is highly sparse, and text embeddings lie on a low-dimensional manifold despite high-dimensional representations. Motivated by these findings, we …
Frozen Lvlms For Micro-Video Recommendation: A Systematic Study Of Feature Extraction And Fusion, Huatuan Sun, Yunshan Ma, Changguang Wu, Yanxin Zhang, Pengfei Wang, Xiaoyu Du
Frozen Lvlms For Micro-Video Recommendation: A Systematic Study Of Feature Extraction And Fusion, Huatuan Sun, Yunshan Ma, Changguang Wu, Yanxin Zhang, Pengfei Wang, Xiaoyu Du
Research Collection School Of Computing and Information Systems
Frozen Large Video Language Models (LVLMs) are increasingly employed in micro-video recommendation (MVR) due to their strong multimodal understanding. However, existing apporches typically deploy LVLMs as fixed black-box feature extractors without systematically comparing alternative representation strategies. To address this gap, we present the first systematic empirical study on various feature extraction paradigms and integration strategies, along with hierarchical representations from frozen LVLMs for MVR. Extensive experiments on representative LVLMs reveal that hidden states from multiple decoder layers provide richer and more effective representations for MVR. Guided by this insight, we propose the Dual Feature Fusion (DFF) Framework, a lightweight approach …
“Grandpa, Can You Speak Nicer?”: Envisioned Chatbot Roles And Design Tensions In Intergenerational Communication Conflicts, Tianyi Zhang, Emran Bin Elias Poh, Yueyue Hou, Yi-Chieh Lee, Renwen Zhang, Jiannan Li, Anthony Tang
“Grandpa, Can You Speak Nicer?”: Envisioned Chatbot Roles And Design Tensions In Intergenerational Communication Conflicts, Tianyi Zhang, Emran Bin Elias Poh, Yueyue Hou, Yi-Chieh Lee, Renwen Zhang, Jiannan Li, Anthony Tang
Research Collection School Of Computing and Information Systems
Intergenerational conversations often break down when differences in tone, language, or expectations lead participants to feel dismissed or misunderstood. In this work, we explore how people envision AI-driven chatbot interventions for addressing communication problems in text-based intergenerational family chat. We conducted a scenario-based design interview with 10 pairs of family members from different generations, in which participants designed chatbot interventions that varied in intervention target and timing. Our findings show that participants expect chatbots to perform multiple themes of intervention, including mediating understanding, providing emotional support, offering evaluative commentary, and guiding interaction through behavioral suggestions. These expectations varied systematically across …
Group Conversational Agents: A Review Of Designs That Support And Shape Group Interaction, Shunyi Yeo, Tianyi Zhang, Scott Bateman, Gary Hsieh, Young-Ho Kim, Simon Tangi Perrault, Jiannan Li, Anthony Tang
Group Conversational Agents: A Review Of Designs That Support And Shape Group Interaction, Shunyi Yeo, Tianyi Zhang, Scott Bateman, Gary Hsieh, Young-Ho Kim, Simon Tangi Perrault, Jiannan Li, Anthony Tang
Research Collection School Of Computing and Information Systems
Conversational agents that participate in or mediate group interaction introduce challenges that extend beyond supporting individual users, raising new questions about how agents participate in and influence groups. To characterise this emerging design space, we present a systematic review of 53 peer-reviewed studies on group conversational agents (GCAs). We analyse how GCAs intervene in group-level processes, including participation regulation, conflict mediation, task alignment, and execution support. Using concepts from group research as an analytic lens, we organise prior GCA work around recurring group interactional challenges (orientation, conflict, alignment, and execution), and examine the roles agents are designed to play in …
Language Embeddings Meet Shallow Autoencoders, Rodrigo Alves, Vojtěch Vančura, Pavel Kordík, Antoine Ledent
Language Embeddings Meet Shallow Autoencoders, Rodrigo Alves, Vojtěch Vančura, Pavel Kordík, Antoine Ledent
Research Collection School Of Computing and Information Systems
Shallow autoencoders are appealing recommenders due to their simplicity, scalability, and competitive retrieval quality, but they struggle in strict cold-start settings where new items have no interactions. We propose an inductive shallow autoencoder that leverages item side information (language embeddings) by fixing the decoder to item features and learning only an encoder in the same semantic space. To prevent trivial self-reconstruction without enforcing a hard zero diagonal, we introduce diagonal gating: a leave-one-item-out objective that blocks the self-copy shortcut only for the item being updated while retaining context from the rest of the user history. An alternating-style optimization trains the …
Context Matters: Auditing Gender Bias In T2i Generation Through Risk-Tiered Use-Case Profiles, Jose Luis Luna Campoverde, Yankun Wu, Xiaofei Xie, Noa Garcia
Context Matters: Auditing Gender Bias In T2i Generation Through Risk-Tiered Use-Case Profiles, Jose Luis Luna Campoverde, Yankun Wu, Xiaofei Xie, Noa Garcia
Research Collection School Of Computing and Information Systems
Text-to-image (T2I) generative models are increasingly used to produce content for education, media, and public-facing communication, and are starting to be integrated into higher-impact pipelines. Since generated images tend to reinforce stereotypes, producing representational erasure via “default” depictions and shaping perceptions of who belongs in certain roles, a growing body of work has proposed metrics to quantify gender bias in T2I outputs. Yet existing evaluations remain fragmented. Metrics are often reported without a shared view of what they measure, what assumptions they entail, or how their results should be interpreted under different deployment contexts. This limits the usefulness of gender …
Rc-Nf: Robot-Conditioned Normalizing Flow For Real-Time Anomaly Detection In Robotic Manipulation, Shijie Zhou, Bin Zhu, Jiarui Yang, Xiangyu Zhao, Jingjing Chen, Yu-Gang Jiang
Rc-Nf: Robot-Conditioned Normalizing Flow For Real-Time Anomaly Detection In Robotic Manipulation, Shijie Zhou, Bin Zhu, Jiarui Yang, Xiangyu Zhao, Jingjing Chen, Yu-Gang Jiang
Research Collection School Of Computing and Information Systems
Recent advances in Vision-Language-Action (VLA) models have enabled robots to execute increasingly complex tasks. However, VLA models trained through imitation learning struggle to operate reliably in dynamic environments and often fail under Out-of-Distribution (OOD) conditions. To address this issue, we propose Robot-Conditioned Normalizing Flow(RC-NF), a real-time monitoring model for robotic anomaly detection and intervention that ensures the robot's state and the object's motion trajectory align with the task. RC-NF decouples the processing of task-aware robot and object states within the normalizing flow. It requires only positive samples for unsupervised training and calculates accurate robotic anomaly scores during inference through the …
Anatomical Domain Shifts: Test-Time Heterogeneous Adaptation For 3d Human Pose Prediction, Qiongjie Cui, Pan Zhou, Jingjing Chen, Na Zhao
Anatomical Domain Shifts: Test-Time Heterogeneous Adaptation For 3d Human Pose Prediction, Qiongjie Cui, Pan Zhou, Jingjing Chen, Na Zhao
Research Collection School Of Computing and Information Systems
The research frontier in human pose prediction (HPP) is advancing toward continual test-time adaptation (TTA), where models must self-adapt to dynamic test distributions. To date, the homeostatic continual TTA remains the sole viable solution, which isolates the model parameters and update domain-sensitive ones. Despite mitigating full-body domain gaps, human anatomical heterogeneity (domain shifts often localize to specific regions) is ignored. This anatomical-agnostic approach forces uniform parameter adaptation across kinematically distinct segments, causing: over-adaptation of stable regions and under-adaptation of shift-prone articulations. To address it, we introduce TT-HA, a novel Test-Time Heterogeneous Adaptation that implicitly estimates domain changes for anatomical segments, …
History To Future: Evolving Agent With Experience And Thought For Zero-Shot Vision-And-Language Navigation, Guangzhao Dai, Shuo Wang, Zihan Wang, Guo-Sen Xie, Yang Yang, Jinshan Pan, Qianru Sun, Xiangbo Shu
History To Future: Evolving Agent With Experience And Thought For Zero-Shot Vision-And-Language Navigation, Guangzhao Dai, Shuo Wang, Zihan Wang, Guo-Sen Xie, Yang Yang, Jinshan Pan, Qianru Sun, Xiangbo Shu
Research Collection School Of Computing and Information Systems
Vision-and-Language Navigation in Continuous Environment (VLN-CE) requires an agent to follow language instructions to navigate the target destination. With the advancement of large language models (LLMs), recent efforts have explored adapting them for zero-shot VLN-CE, offering a promising solution in addressing the drawbacks of poor generalization in the training-based paradigm. However, existing LLM-based works primarily perform naive reasoning for decision-making and lack feedback, e.g., reviewing historical errors and predicting future potentials. Consequently, it may suffer from continuous failure for those initial error tasks. In this paper, we rethink LLM-based zero-shot VLN-CE and propose a new paradigm, named EvoNav, to improve …
Adaptive Outlier Detection Over Data Stream, Rui Zhu, Mingyuan Jiang, Xiaochun Yang, Baihua Zheng, Bin Wang, Tao Qiu
Adaptive Outlier Detection Over Data Stream, Rui Zhu, Mingyuan Jiang, Xiaochun Yang, Baihua Zheng, Bin Wang, Tao Qiu
Research Collection School Of Computing and Information Systems
Continuous distance-based outlier detection in streaming data poses significant challenges and has a wide range of practical applications. Traditional threshold-based methods perform well under stable streaming conditions, where fixed parameters remain effective. However, they often struggle with dynamic data distributions and high stream speeds, leading to suboptimal performance, limited control over the number of returned outliers, and failure to meet real-time detection requirements. To address these issues, this paper introduces a novel Recall and Proportion-Aware Outlier Detection (RPA-OD) query. In RPA-OD, ρ defines a distance relaxation that enables real-time outlier detection. Specifically, objects with fewer than k neighbors within the …
Task Complexity Matters: An Empirical Study Of Reasoning In Llms For Sentiment Analysis, Donghao Huang, Zhaoxia Wang
Task Complexity Matters: An Empirical Study Of Reasoning In Llms For Sentiment Analysis, Donghao Huang, Zhaoxia Wang
Research Collection School Of Computing and Information Systems
Large language models (LLMs) with reasoning capabilities have fueled a compelling narrative that reasoning universally improves performance across language tasks. We test this claim through a comprehensive evaluation of 504 configurations across seven model families—including adaptive, conditional, and reinforcement learning-based reasoning architectures—on sentiment analysis datasets of varying granularity (binary, five-class, and 27-class emotion). Our findings reveal that reasoning effectiveness is strongly task-dependent, challenging prevailing assumptions: (1) Reasoning shows task-complexity dependence—binary classification degrades up to -19.9 F1% points (pp), while 27-class emotion recognition gains up to +16.0 pp; (2) Distilled reasoning variants underperform base models by 3–18 pp on simpler tasks, …
A Novel Hierarchical Multi-Agent System For Payments Using Llms, Donghao Huang, Joon Kiat Chua, Zhaoxia Wang
A Novel Hierarchical Multi-Agent System For Payments Using Llms, Donghao Huang, Joon Kiat Chua, Zhaoxia Wang
Research Collection School Of Computing and Information Systems
Large language model (LLM) agents, such as OpenAI’s Operator and Claude’s Computer Use, can automate workflows but unable to handle payment tasks. Existing agentic solutions have gained significant attention; however, even the latest approaches face challenges in implementing end-to-end agentic payment workflows. To address this gap, this research proposes the Hierarchical Multi-Agent System for Payments (HMASP), which provides an end-to-end agentic method for completing payment workflows. The proposed HMASP leverages either open-weight or proprietary LLMs and employs a modular architecture consisting of the Conversational Payment Agent (CPA - first agent level), Supervisor agents (second agent level), Routing agents (third agent …
Enhancing Pointing Gestures Of Non-Hmd Users In Asymmetric Collocated Mixed Reality Collaboration, Nam-Dang Vo, Van-Vinh Thai, Anthony Tang, Khanh-Duy Le
Enhancing Pointing Gestures Of Non-Hmd Users In Asymmetric Collocated Mixed Reality Collaboration, Nam-Dang Vo, Van-Vinh Thai, Anthony Tang, Khanh-Duy Le
Research Collection School Of Computing and Information Systems
A common collocated group setting in mixed-reality (MR) collaboration is a person wearing a MR headset (HMD user) and presenting MR contents to audiences who are not provided with such specialized devices (Non-HMD users). In this setting, while Non-HMD users can view the MR environment shown on a large physical display, it still remains challenging for the HMD user to interpret their pointing gesture when they spatially refer to objects in the MR environment. To address this, we designed and evaluated two pointing techniques—SCREEN and SCREEN+SPACE—that support Non-HMD users in referring to MR content. Screen pointing allows users to refer …