Artificial Intelligence and Robotics Commons^™

Eformer: An Effective Edge-Based Transformer For Vehicle Routing Problems, Dian Meng, Zhiguang Cao, Yaoxin Wu, Yaqing Hou, Hongwei Ge, Qiang Zhang

Research Collection School Of Computing and Information Systems

Recent neural heuristics for the Vehicle Routing Problem (VRP) primarily rely on node coordinates as input, which may be less effective in practical scenarios where real cost metrics--such as edge-based distances--are more relevant. To address this limitation, we introduce EFormer, an Edge-based Transformer model that uses edge as the sole input for VRPs. Our approach employs a precoder module with a mixed-score attention mechanism to convert edge information into temporary node embeddings. We also present a parallel encoding strategy characterized by a graph encoder and a node encoder, each responsible for processing graph and node embeddings in distinct feature spaces, …

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 …

Connecting Giants: Synergistic Knowledge Transfer Of Large Multimodal Models For Few-Shot Learning, Hao Tang, Shengfeng He, Jing Qin

Research Collection School Of Computing and Information Systems

Few-shot learning (FSL) addresses the challenge of classifying novel classes with limited training samples. While some methods leverage semantic knowledge from smaller-scale models to mitigate data scarcity, these approaches often introduce noise and bias due to the data's inherent simplicity. In this paper, we propose a novel framework, Synergistic Knowledge Transfer (SYNTRANS), which effectively transfers diverse and complementary knowledge from large multimodal models to empower the off-the-shelf few-shot learner. Specifically, SYNTRANS employs CLIP as a robust teacher and uses a few-shot vision encoder as a weak student, distilling semantic-aligned visual knowledge via an unsupervised proxy task. Subsequently, a training-free synergistic …

Xfinbench: Benchmarking Llms In Complex Financial Problem Solving And Reasoning, Zhihan Zhang, Yixin Cao, Lizi Liao

Research Collection School Of Computing and Information Systems

Solving financial problems demands complex reasoning, multimodal data processing, and a broad technical understanding, presenting unique challenges for current large language models (LLMs). We introduce **XFinBench**, a novel benchmark with 4,235 examples designed to evaluate LLM’s ability in solving comple**X**, knowledge-intensive **Fin**ancial problems across diverse graduate-level finance topics with multi-modal context. We identify five core capabilities of LLMs using XFinBench, i.e., _terminology understanding_, _temporal reasoning_, _future forecasting_, _scenario planning_, and _numerical modelling_. Upon XFinBench, we conduct extensive experiments on 18 leading models. The result shows that o1 is the best-performing text-only model with an overall accuracy of 67.3%, but still …

Taclr: A Scalable And Efficient Retrieval-Based Method For Industrial Product Attribute Value Identification, Yindu Su, Huike Zou, Lin Sun, Ting Zhang, Haiyang Yang, Chen Li Yu, David Lo, Qingheng Zhang, Shuguang Han, Jufeng Chen

Research Collection School Of Computing and Information Systems

Product Attribute Value Identification (PAVI) involves identifying attribute values from product profiles, a key task for improving product search, recommendation, and business analytics on e-commerce platforms. However, existing PAVI methods face critical challenges, such as inferring implicit values, handling outof-distribution (OOD) values, and producing normalized outputs. To address these limitations, we introduce Taxonomy-Aware Contrastive Learning Retrieval (TACLR), the first retrieval-based method for PAVI. TACLR formulates PAVI as an information retrieval task by encoding product profiles and candidate values into embeddings and retrieving values based on their similarity. It leverages contrastive training with taxonomy-aware hard negative sampling and employs adaptive inference …

Starpose: 3d Human Pose Estimation Via Spatial-Temporal Autoregressive Diffusion, Haoxin Yang, Weihong Chen, Xuemiao Xu, Cheng Xu, Peng Xiao, Cuifeng Sun, Shaoyu Huang, Shengfeng He

Research Collection School Of Computing and Information Systems

Monocular 3D human pose estimation remains a challenging task due to inherent depth ambiguities and occlusions. Compared to traditional methods based on Transformers or Convolutional Neural Networks (CNNs), recent diffusionbased approaches have shown superior performance, leveraging their probabilistic nature and high-fidelity generation capabilities. However, these methods often fail to account for the spatial and temporal correlations across predicted frames, resulting in limited temporal consistency and inferior accuracy in predicted 3D pose sequences. To address these shortcomings, this paper proposes StarPose, an autoregressive diffusion framework that effectively incorporates historical 3D pose predictions and spatialtemporal physical guidance to significantly enhance both the …

Sifar: A Simple Faster Accelerated Variance‑Reduced Gradient Method, Zhize Li

Research Collection School Of Computing and Information Systems

In this paper, we propose a simple faster accelerated gradient method called SIFAR for solving the finite-sum optimization problems. Concretely, we consider both general convex and strongly convex settings: i) For general convex finite-sum problems, SIFAR improves previous state-of-the-art result given by Varag. In particular, for large-scale problems or the convergence error is not very small, SIFAR obtains the first optimal result O(n), matching the lower bound. ii) For strongly convex finite-sum problems, we also show that SIFAR can achieve the optimal convergence rate matching the lower bound. Besides, SIFAR enjoys a simpler loopless algorithmic structure while previous algorithms use …

From Risk To Resilience: Towards Assessing And Mitigating The Risk Of Data Reconstruction Attacks In Federated Learning, Xiangrui Xu, Zhize Li, Yufei Han, Bin Wang, Jiqiang Liu, Wei Wang

Research Collection School Of Computing and Information Systems

Data Reconstruction Attacks (DRA) pose a significant threat to Federated Learning (FL) systems by enabling adversaries to infer sensitive training data from local clients. Despite extensive research, the question of how to characterize and assess the risk of DRAs in FL systems remains unresolved due to the lack of a theoretically-grounded risk quantification framework. In this work, we address this gap by introducing Invertibility Loss (InvLoss) to quantify the maximum achievable effectiveness of DRAs for a given data instance and FL model. We derive a tight and computable upper bound for InvLoss and explore its implications from three perspectives. First, …

L2m2: A Hierarchical Framework Integrating Large Language Model And Multi‑Agent Reinforcement Learning, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Lin Li, Xin Zhao, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Multi-agent reinforcement learning (MARL) has demonstrated remarkable success in collaborative tasks, yet faces significant challenges in scaling to complex scenarios requiring sustained planning and coordination across long horizons. While hierarchical approaches help decompose these tasks, they typically rely on hand-crafted subtasks and domain-specific knowledge, limiting their generalizability. We present L2M2, a novel hierarchical framework that leverages large language models (LLMs) for high-level strategic planning and MARL for low-level execution. L2M2 enables zero-shot planning that supports both end-to-end training and direct integration with pre-trained MARL models. Experiments in the VMAS environment demonstrate that L2M2's LLM-guided MARL achieves superior performance while requiring …

Ai-Assisted Risk Assessment In Generative Ai Governance, Wu Jiaqi Young, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Effective risk assessment is paramount for responsible generative AI (GenAI) deployment. Traditional governance approaches that rely on manual reviews are inadequate given the scale and velocity of GenAI outputs. A risk-based approach incorporating real-time monitoring and governance is paramount. In this research, we examine how the efficacy of suggestive versus supportive explanations for AI’s risk assessment of GenAI outputs is moderated by user domain expertise and AI’s risk assessment in determining user acceptance. We hypothesize that cognitive involvement increases with AI’s risk assessment, with higher risks triggering more critical evaluation. By drawing on the elaboration likelihood model, we hypothesize that …

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 …

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 …

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 …

Role Of Social Media Mindfulness In Combatting Fake News Propagation, Gaurav Bansal, Fiona Fui-Hoon Nah, Jason B. Thatcher

Research Collection School Of Computing and Information Systems

The dissemination of fake news by social media users is a key factor in the escalation of misinformation. Research suggests that social media networks are becoming increasingly homophilic, which leads to an overreliance on social media friends that contributes to the spread of fake news. However, little is known about how social media mindfulness can reduce the sharing of fake news. To investigate this research question, we conceptualized a social media mindfulness construct and developed the social media mindfulness scale. We also hypothesize that social media mindfulness lowers overreliance on friends’ knowledge, which increases skepticism about social media news that …

Zero-Shot Generalist Graph Anomaly Detection With Unified Neighborhood Prompts, Chaoxi Niu, Hezhe Qiao, Changlu Chen, Ling Chen, Guansong Pang

Research Collection School Of Computing and Information Systems

Graph anomaly detection (GAD), which aims to identify nodes in a graph that significantly deviate from normal patterns, plays a crucial role in broad application domains. However, existing GAD methods are one-model-for-one-dataset approaches, i.e., training a separate model for each graph dataset. This largely limits their applicability in real-world scenarios. To overcome this limitation, we propose a novel zero-shot generalist GAD approach UNPrompt that trains a one-for-all detection model, requiring the training of one GAD model on a single graph dataset and then effectively generalizing to detect anomalies in other graph datasets without any retraining or fine-tuning. The key insight …

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 …

Ai-Enhanced Structured Literacy Intervention For Secondary Students: A Case Study Of Science Of Reading, Jennifer Bird

Teaching & Learning Faculty Publications

This study examines the effectiveness of Lexia PowerUp, an AI-powered literacy program, for sixth-grade students requiring Tier 3 reading intervention. Seven sixth-grade students (six boys, one girl; five African American, two Caucasian; all qualifying for free/reduced lunch) participated in a six-month intervention combining 50 minutes of daily small-group instruction with individualized Lexia PowerUp usage. Researchers measured progress through Achieve 3000 Lexile assessments and Lexia PowerUp performance data across three skill strands: Word Study, Grammar, and Comprehension. All participants demonstrated Lexile level improvements from beginning-of-year to mid-year assessments, though students remained below sixth-grade benchmarks (925-1070L). Analysis of Lexia PowerUp progression showed …

Towards Securing Ai Systems: Investigating Threats In Multimodal Autonomous Driving & Rag Systems, Saket Sanjeev Chaturvedi

All Dissertations

Artificial Intelligence (AI) systems have become central to high-stakes applications such as autonomous driving and language-based decision support. As their deployment accelerates, ensuring the security and trustworthiness of these systems becomes paramount. Among the most stealthy and potent threats are backdoor attacks, where models behave as expected under normal conditions but exhibit malicious behavior when triggered by specific inputs, either digital or physical.

This thesis investigates novel backdoor and adversarial vulnerabilities across two emerging classes of AI architectures: (1) multimodal 3D object detection systems that fuse LiDAR and camera data, and (2) Retrieval-Augmented Generation (RAG) systems that pair large language …

Wildfires Classification In Canadian Boreal Forest: A Comparative Study Of Logistic Regression And Xgboost Models, Brandon Tran, Elijah James Duran, Mike Luu, Hesham Morgan, Surendra Maharjan, Wenzhao Li, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

In recent years, Canada has faced a growing number of wildfires. These events have devastated ecosystems, displaced communities, and posed severe health risks. To minimize the damage caused by such disasters, this study aims to develop an early warning system that predicts wildfire occurrences. Two machine learning models for binary classification of wildfire occurrence in Canadian wild forests, Logistic regression and XGBoost, will be compared and evaluated. The models are used to predict the likelihood of wildfire events based on various environmental and climatic factors. The models are evaluated using a 70-30 split validation approach and their performance is assessed …

Characterization Of Search Spaces And Effects On Machine Learning, Leo Ghelarducci

Doctoral Dissertations and Master's Theses

The present status of the field of Machine Learning (ML) focuses on optimization of popular models. Rarely are the effects of the problem characteristics upon the solution algorithm studied. There exists no standard for knowing when to apply ML algorithms to a given problem or how to estimate the effectiveness of results. Focusing on the search space of problems, a rigorous study was conducted to generate an in-depth understanding of the impact of search space characteristics to the performance of a ML algorithm, specifically a Genetic Algorithm (GA). The effects of specific problem characteristics, represented via solution space characteristics, on …