Digital Commons Network^™

The Complexity Of Long-Distance Dependencies And Their Impact On Language Models, Abhijit Shrikant Mahalunkar

Doctoral

Sequential data modeling is an important challenge in various fields and in particular in natural language processing. Building effective sequential models faces a notable challenge in the form of Long-Distance Dependencies (LDDs) within the sequence data. Hence, successfully overcoming this challenge is imperative for developing robust and accurate sequential models across various domains and applications. To tackle this challenge, the first step is to conduct a detailed analysis of the complexity of LDDs observed in various sequence datasets. This thesis offers a thorough exploration and documentation of this analysis. An important finding from this thesis is the consistent patterns of …

Analysis Of The Status And Thematic Trends Of Ai For Science Research Abroad From 2015 To 2024, Fangyuan Wang, Huiting Xu, Jinghua Xue

Journal of Scientific Information Research

[Purpose/significance] This paper analyzes the relevant literature in the field of AI for Science（AI4S）in the WoS core database from 2015 to 2024, and sorts out the research status and development trends in this field, aiming to provide forward-looking insights for the application of AI technology in scientific research.

[Method/process] This paper combines bibliometric analysis with the BERTopic model to analyze the publication trends, publishing countries, core authors, and topic identification and development trends in the field of AI4S.

[Result/conclusion] Through bibliometric analysis, this paper reveals the exponential growth trend of AI4S-related literature, and finds that China ranks first in the …

Thesis: Comparing Functional And Effective Brain Connectivity Metrics For Eeg, Diksha Srishyla

Theses and Dissertations

Background:Brain connectivity measures have been used to study communication between brain regions using electroencephalography (EEG). Functional and effective connectivity estimate the synchronization and the flow of information between regions, respectively. However, findings from studies using different measures to investigate similar connections do not converge. To guide the selection of functional and effective connectivity measures in future studies, we systematically compared a set of measures in the context of resting state EEG. We examined four functional connectivity metrics (coherence (Coh), the imaginary part of coherence (imCoh), the corrected imaginary part of phase lagged value (ciPLV), the debiased weighted phase-locking index (dwPLI)) …

Multi-Perspective Feature Learning For Facial Expression Recognition In The Wild, Xiangyu Hu

Theses and Dissertations

With the rapid progress of deep learning, Facial Expression Recognition (FER) has seen substantial improvements in performance, particularly “in the wild” meaning real world conditions. Despite these advances, most existing methods extract features from facial images as the sole emotional cues, which limits the model’s ability to capture the full complexity of human emotional expressions.

In reality, facial expressions are composed of diverse and multi-perspective information, including appearance-based cues and geometric structural deformations due to activations of facial muscles. Depending exclusively on one type of representation may fail to exploit the complementary nature of these cues, an issue that becomes …

A Data-Driven Framework For Optimal Retail Store Location, Ming Hui Tan

Dissertations and Theses Collection (Open Access)

This study develops a data-driven framework for optimal retail store location planning that integrates road network analysis, mobility data and optimization techniques. By addressing the limitations of traditional approaches that rely on outdated census data and manual site selection, this research offers a scalable and adaptable solution for retail expansion in diverse urban environments. Chapters 1 and 2 establish the foundational context and theoretical underpinnings of this research. Chapter 1 introduces the research problem and motivation, highlighting the limitations of existing approaches and defining three key research objectives: automating candidate site identification, improving footfall estimation, and developing a scalable multi-site …

Harnessing Se Community Knowledge For Developer-Centric Code Intelligence, Chengran Yang

Dissertations and Theses Collection (Open Access)

The integration of Large Language Models (LLMs), particularly those tailored for programming tasks—referred to as code LLMs—has created novel opportunities to enhance developer productivity. These advanced models automate routine and repetitive coding tasks, such as code generation and debugging, and enable faster prototyping and more efficient problem-solving. Despite these remarkable advantages, the current generation of code LLMs exhibits notable limitations that impact their practical effectiveness in real-world software engineering scenarios. These models frequently produce code that is inefficient or suboptimal in runtime performance, demonstrate opaque reasoning processes, and struggle to adapt effectively to diverse developer contexts and specific requirements. Moreover, …

Look Before You Decide: Prompting Active Deduction Of Mllms For Assumptive Reasoning, Yian Li, Wentao Tian, Yang Jiao, Jingjing Chen, Tianwen Qian, Bin Zhu, Na Zhao, Yu‑Gang Jiang

Research Collection School Of Computing and Information Systems

Recently, Multimodal Large Language Models (MLLMs) have achieved significant success across multiple disciplines due to their exceptional instruction-following capabilities and extensive world knowledge. However, whether these MLLMs possess human-like compositional reasoning abilities remains an open problem. To unveil their reasoning behaviors, we first curate a Multimodal Assumptive Reasoning Benchmark (MARS-Bench) in this paper. Interestingly, we find that most prevalent MLLMs can be easily fooled by the introduction of a presupposition into the question, whereas such presuppositions appear naive to human reasoning. Besides, we also propose a simple yet effective method, Active Deduction (AD), a novel reinforcement learning paradigm to encourage …

From Holistic To Localized: Local Enhanced Adapters For Efficient Visual Instruction Fine-Tuning, Pengkun Jiao, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yugang Jiang

Research Collection School Of Computing and Information Systems

Efficient Visual Instruction Fine-Tuning (EVIT) seeks to adapt Multimodal Large Language Models (MLLMs) to downstream tasks with minimal computational overhead. However, as task diversity and complexity increase, EVIT faces significant challenges in resolving data conflicts. To address this limitation, we propose the Dual Low-Rank Adaptation (Dual-LoRA), a holistic-to-local framework that enhances the adapter’s capacity to address data conflict through dual structural optimization. Specifically, we utilize two subspaces: a skill space for stable, holistic knowledge retention, and a rank-rectified task space that locally activates the holistic knowledge. Additionally, we introduce Visual Cue Enhancement (VCE), a multi-level local feature aggregation module designed …

Exploring Object Status Recognition For Recipe Progress Tracking In Non-Visual Cooking, Franklin Mingzhe Li, Kaitlyn Ng, Bin Zhu, Patrick Carrington

Research Collection School Of Computing and Information Systems

Cooking plays a vital role in everyday independence and well-being, yet remains challenging for people with vision impairments due to limited support for tracking progress and receiving contextual feedback. Object status — the condition or transformation of ingredients and tools — offers a promising but underexplored foundation for context-aware cooking support. In this paper, we present OSCAR (Object Status Context Awareness for Recipes), a technical pipeline that explores the use of object status recognition to enable recipe progress tracking in non-visual cooking. OSCAR integrates recipe parsing, object status extraction, visual alignment with cooking steps, and time-causal modeling to support real-time …

Visual-Enhanced Multimodal Framework For Flexible Job Shop Scheduling Problem, Peng Zhao, Zhiguang Cao, Di Wang, Wen Song, Wei Pang, You Zhou, Yuan Jiang

Research Collection School Of Computing and Information Systems

Multimodal models leverage complementary information across modalities to enrich feature representations. While visual information shows potential in representing structure for some combinatorial optimization problems (COPs), its application to complex scheduling like the Flexible Job Shop Scheduling Problem (FJSP) remains underexplored. Current learning-based FJSP solvers predominantly rely on handcrafted state features. This dependence can lead to inconsistencies and may not fully capture the problem's intricate dynamics. Crucially, these methods overlook visual modalities. Visual representations offer a distinct advantage by inherently capturing the global topological structure and complex resource interactions within the FJSP state. Unlike localized handcrafted features, this holistic, structural view …

Mitigating Cross-Modal Representation Bias For Multicultural Image-To-Recipe Retrieval, Qing Wang, Chong-Wah Ngo, Yu Cao, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Existing approaches for image-to-recipe retrieval have the implicit assumption that a food image can fully capture the details textually documented in its recipe. However, a food image only reflects the visual outcome of a cooked dish and not the underlying cooking process. Consequently, learning cross-modal representations to bridge the modality gap between images and recipes tends to ignore subtle, recipe-specific details that are not visually apparent but are crucial for recipe retrieval. Specifically, the representations are biased to capture the dominant visual elements, resulting in difficulty in ranking similar recipes with subtle differences in use of ingredients and cooking methods. …

Art4math: Handwritten Mathematical Expression Recognition Via Multimodal Sketch Grounding, Yang Zhou, Jin Wang, Yuxiao Zhang, Kaixiang Huang, Guodong Lu, Jingru Yang, Shengfeng He

Research Collection School Of Computing and Information Systems

Handwritten Mathematical Expression Recognition (HMER) remains a challenging task due to the structural complexity of mathematical notation and the ambiguity of handwritten symbols-e.g., ''ρ'' vs. ''p'' or ''B'' vs. ''β''. While stroke-based models offer disambiguation via temporal cues, most existing methods are constrained by coarse modality fusion and a lack of fine-grained cross-modal alignment, further hindered by limited annotated data. We introduce Art for Math (Art4Math), a novel framework that leverages the structural richness of human sketches to enhance HMER through fine-grained, modality-aware learning. Art4Math follows a two-stage training paradigm: Art Grounding (A-Grd) and Math Decoding (M-Dec). In A-Grd, the …

Emoshortcuts: Emotionally Expressive Body Augmentation For Social Mixed Reality Avatars, Hyuna Seo, Youngki Lee, Rajesh Krishna Balan, Thivya Kandappu

Research Collection School Of Computing and Information Systems

We present EmoShortcuts1, a novel social Mixed Reality (MR) framework that enhances emotional expression by dynamically augmenting avatar body gestures to reflect users’ emotional states. While social MR enables immersive remote interactions through avatars, conveying emotions remains challenging due to limitations in head-mounted display (HMD) tracking (e.g., missing lower-body movements, such as stomping or defensive postures), and users’ tendency to deprioritize nonverbal expressions during multitasking. EmoShortcuts addresses these challenges by introducing an augmentation framework that generates expressive body gestures even when users’ physical movements are restricted. We conducted a formative study with 12 participants to identify key challenges in emotional …

Language-Driven 3d Human Pose Estimation In Multi-Person Scenarios: A New Dataset And Approach, Tingrui Shen, Bangzhen Liu, Zhirun Fan, Shiting Zhang, Weifeng Pan, Sun Fan, Dan Cao, Shengfeng He

Research Collection School Of Computing and Information Systems

In an NBA game scenario, consider the challenge of locating and analyzing the 3D poses of players performing a user-specified action, such as attempting a shot. Traditional 3D human pose estimation (3DHPE) methods often fall short in such complex, multi-person scenes due to their lack of semantic integration and reliance on isolated pose data. To address these limitations, we introduce Language-Driven 3D Human Pose Estimation (L3DHPE), a novel approach that extends 3DHPE to general multi-person contexts by incorporating detailed language descriptions. We present Panoptic-L3D, the first dataset designed for L3DHPE, featuring 3,838 linguistic annotations for 1,476 individuals across 588 videos, …

Advances In Iot, Ai, And Sensor‑Based Technologies For Disease Treatment, Health Promotion, Successful Ageing, And Ageing Well, Yuzhou Qian, Keng Siau

Research Collection School Of Computing and Information Systems

Recent advancements in the Internet of Things (IoT) and artificial intelligence (AI) are unlocking transformative opportunities across society. One of the most critical challenges addressed by these technologies is the ageing population, which presents mounting concerns for healthcare systems and quality of life worldwide. By supporting continuous monitoring, personal care, and data-driven decision-making, IoT and AI are shifting healthcare delivery from a reactive approach to a proactive one. This paper presents a comprehensive overview of IoT-based systems with a particular focus on the Internet of Healthcare Things (IoHT) and their integration with AI, referred to as the Artificial Intelligence of …

Website Owner Identification Through Multi-Level Contrastive Representation Learning, Cheng Tu, Yunshan Ma, Yang Li, Min Zhang, Miao Hu, Fan Shi, Xiang Wang

Research Collection School Of Computing and Information Systems

Website owner identification aims to recognize the organization or individual who owns a given website that is served on the web. It is a crucial step for cyberspace surveying and mapping, playing a significant role in cyberspace administration and governance. Existing widely employed solutions for website owner identification mainly fall into two paradigms: (1) querying the public information databases such as WHOIS, which store the Internet resource’s registered users or assignees; and (2) directly extracting the organization or individual name of the website owner from the webpage using the technique of named entity recognition. However, the former is less reliable …

Morphology-Aware Hrv Estimation From Wrist Ppg In Sedentary Scenarios, Changshuo Hu, Hung Manh Pham, Dong Ma

Research Collection School Of Computing and Information Systems

Photoplethysmography (PPG) is widely used in wearable devices for non-invasive heart rate variability (HRV) monitoring. While most prior work focuses on mitigating motion artifacts, recent studies highlight that even subtle contact pressure variations can distort waveform morphology and lead to inaccurate HRV estimates. In this work, we propose a morphology-aware deep learning framework that conditions HRV estimation on beat-level waveform types. Our model jointly encodes the raw PPG waveform and a sequence of pressure-induced morphology labels using parallel encoders, integrates them via cross-attention, and predicts normal-to-normal (NN) intervals and beat count to support downstream HRV computation. Evaluated on the public …

Trust And Ethics In Ai-Driven E-Commerce: Persuasion Vs. Privacy, Akriti Nepal

Student Publications

This study examines how AI-driven features in e-commerce influence user satisfaction and the role of trust in these interactions. Using a survey-based dataset of 100 consumers, we investigated whether trust moderates or mediates the impact of AI persuasiveness and perceptions of bias, intrusiveness, and preference understanding on satisfaction. Results indicate that AI’s perceived ability to understand user preferences strongly predicts satisfaction, while trust partially mediates the relationship between helpful AI features and urgency messages and user satisfaction. Conversely, trust did not significantly moderate these relationships, and concerns about bias and intrusiveness had minimal impact. Findings suggest that AI-driven satisfaction is …

Application Of Machine Learning For Vascular System Analysis, Alireza Bagheri Rajeoni

Theses and Dissertations

The analysis of vascular structures is critical for diagnosing, monitoring, and treating vascular diseases such as aneurysms, stenosis, and vascular calcification. Traditional methods often rely on manual interpretation of imaging data, which is time-consuming, subjective, and not scalable. This work explores the application of advanced machine learning techniques to automate and enhance vascular system analysis. Our contributions include achieving state-of-the-art accuracy in vascular segmentation, developing a machine learning pipeline to automatically quantify vascular calcification in peripheral arterial disease, and designing a multi-stage machine learning system for abdominal aortic aneurysm analysis that identifies aneurysm boundaries and estimates aneurysm volume in a …

Governance In The Absence Of Government, Tracy Hresko Pearl

Faculty Articles

Artificial intelligence (AI) is advancing at an unprecedented pace, with generative systems exerting growing influence over social, economic, and political life. While Al offers opportunities for innovation and efficiency, it also poses risks ranging from misinformation and job displacement to existential threats if highly autonomous systems evade human control. Across industry, government, and civil society, there is broad consensus that Al requires oversight.

Yet traditional U.S. regulatory approaches face six significant barriers: (1) technology outpacing legislation, (2) limited Al expertise among policymakers, (3) regulatory capture, (4) political gridlock, (5) outdated governance structures, and (6) the inherent complexity of Al. Combined …

Computational Analogies In The Era Of Large Language Models, Amarakoon Mudiyanselage Thilini Wijesiriwardene

Theses and Dissertations

Analogical reasoning is an important part of human cognition requiring the integration of abstract reasoning, pattern recognition, and background knowledge. Despite significant advances in language modeling, the capacity of current methods to accurately identify, model, and evaluate analogies remains fundamentally underexplored.

Analogies enable individuals to perceive deep similarities between superficially different situations. Effective analogy-making requires integrating knowledge about the external world with abstract reasoning and pattern recognition capabilities. While current language models (LMs), trained on massive textual corpora using autoregressive or masked objectives, achieve impressive performance across Natural Language Processing (NLP) tasks such as text generation, summarization, and classification, their …

Omnivton: Training-Free Universal Virtual Try-On, Zhaotong Yang, Yuhui Li, Shengfeng He, Xinzhe Li, Yangyang Xu, Junyu Dong, Yong Du

Research Collection School Of Computing and Information Systems

Image-based Virtual Try-On (VTON) techniques rely on either supervised in-shop approaches, which ensure high fidelity but struggle with cross-domain generalization, or unsupervised in-the-wild methods, which improve adaptability but remain constrained by data biases and limited universality. A unified, training-free solution that works across both scenarios remains an open challenge. We propose OmniVTON, the first training-free universal VTON framework that decouples garment and pose conditioning to achieve both texture fidelity and pose consistency across diverse settings. To preserve garment details, we introduce a garment prior generation mechanism that aligns clothing with the body, followed by continuous boundary stitching technique to achieve …

Lsfdnet: A Single-Stage Fusion And Detection Network For Ships Using Swir And Lwir, Yanyin Guo, Runxuan An, Junwei Li, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

Traditional ship detection methods primarily rely on single-modal approaches, such as visible or infrared images, which limit their application in complex scenarios involving varying lighting conditions and heavy fog. To address this issue, we explore the advantages of short-wave infrared (SWIR) and long-wave infrared (LWIR) in ship detection and propose a novel single-stage image fusion detection algorithm called LSFDNet. This algorithm leverages feature interaction between the image fusion and object detection subtask networks, achieving remarkable detection performance and generating visually impressive fused images. To further improve the saliency of objects in the fused images and improve the performance of the …

Diffusionmat: Alpha Matting As Deterministic Sequential Refinement Learning, Yangyang Xu, Shengfeng He, Wenqi Shao, Yong Du, Kwan-Yee K. Wong, Yu Qiao, Jun Yu, Ping Luo

Research Collection School Of Computing and Information Systems

In this paper, we introduce DiffusionMat, a novel image matting framework that employs a diffusion model for the transition from coarse to refined alpha mattes. Diverging from conventional methods that utilize trimaps merely as loose guidance for alpha matte prediction, our approach treats image matting as a deterministic sequential refinement learning process. This process begins with the addition of noise to trimaps and iteratively denoises them using a pre-trained diffusion model, which incrementally guides the prediction towards a clean alpha matte. The key innovation of our framework is a correction module that adjusts the output at each denoising step, ensuring …

Fine-Grained Abnormality Prompt Learning For Zero-Shot Anomaly Detection, Jiawen Zhu, Yew‑Soon Ong, Chunhua Shen, Guansong Pang

Research Collection School Of Computing and Information Systems

Current zero-shot anomaly detection (ZSAD) methods show remarkable success in prompting large pre-trained visionlanguage models to detect anomalies in a target dataset without using any dataset-specific training or demonstration. However, these methods often focus on crafting/learning prompts that capture only coarse-grained semantics of abnormality, e.g., high-level semantics like ‘damaged’, ‘imperfect’, or ‘defective’ objects. They therefore have limited capability in recognizing diverse abnormality details that deviate from these general abnormal patterns in various ways. To address this limitation, we propose FAPrompt, a novel framework designed to learn Fine-grained Abnormality Prompts for accurate ZSAD. To this end, a novel Compound Abnormality Prompt …

Hlcg: A Hierarchical Lane-Changing Gaming Decision Model For Heterogeneous Traffic Flow On Two-Lane Highways, Tianyi Wang, Chong He, Hao Li, Yixuan Li, Yiming Xu, Yangyang Wang, Junfeng Jiao

Research Collection College of Integrative Studies

Discretionary lane-changing behavior is one of the most common highway operations, which seriously affects traffic efficiency and safety. Nowadays, connected and automated vehicles (CAVs) are advancing rapidly, though not yet fully widespread. As a result, a mixed traffic environment with traditional human-driven vehicles (HDVs) and CAVs will persist for the foreseeable future. To achieve effective automatic lane-changing maneuvers, it’s necessary to propose a lane-changing decision model for heterogeneous traffic flow on two-lane highways. This paper firstly extends longitudinal car-following models based on the intelligent driver model and lateral lane-changing models using quintic polynomial curves to accommodate heterogeneous traffic flow, and …

Towards A Digital Twin For Smart Resilient Cities: Real-Time Fire And Smoke Tracking And Prediction Platform For Community Awareness (Firecom), Kijin Seong, Junfeng Jiao, Ryan Lewis Hardesty, Arya Farahi, Paul Navratil, Nate Casebeer, Braniff Davis, Justice Jones, Dev Niyogi

Research Collection College of Integrative Studies

This paper discusses the development and application of a digital twin (DT) for urban resilience, focusing on an integrated platform for real-time fire and smoke. The proposed platform, FireCom, adapts DT concepts for the unique challenges of urban fire management, which differ significantly from regional wildfire systems. Through an exploratory case study in Austin, Texas, in the United States, this research bridges the theoretical foundations of 3D DT with their practical application in fire and smoke management. By fusing diverse data sources, ranging from air quality sensors and meteorological data to 3D urban infrastructure, FireCom supports both emergency response and …

Filterfl: Knowledge Filtering-Based Data-Free Backdoor Defense For Federated Learning, Yanxin Yang, Ming Hu, Xiaofei Xie, Yue Cao, Pengyu Zhang, Yihao Huang, Mingsong Chen

Research Collection School Of Computing and Information Systems

As a distributed machine learning paradigm, Federated Learning (FL) enables large-scale clients to collaboratively train a model without sharing their raw data. However, due to the lack of data auditing for untrusted clients, FL is vulnerable to poisoning attacks, especially backdoor attacks. By using poisoned data for local training or directly changing the model parameters, attackers can easily inject backdoors into the model, which can trigger the model to make misclassification of targeted patterns in images. To address these issues, we propose a novel data-free trigger-generation-based defense approach based on the two characteristics of backdoor attacks: i) triggers are learned …

Search Trajectory Network-Enhanced Multi-Objective Dynamic Algorithm Configuration, Robbert Reijnen, Zaharah Bukhsh, Hoong Chuin Lau, Yaoxin Wu, Yingqian Zhang

Research Collection School Of Computing and Information Systems

Deep reinforcement learning (DRL) has emerged as an effective technique for dynamic algorithm configuration, particularly in evolutionary computation, enabling adaptive parameter updates during algorithmic execution. DRL-based methods have shown broad applicability across different problem domains and are designed to configure algorithms without problem-specific information, making them highly transferable across problem variants and scalable to different problem sizes. This paper proposes a novel graph neural network-based approach that learns representations of Search Trajectory Networks (STNs) to track the convergence behavior of multiple objectives and dynamically reconfigures multiobjective evolutionary algorithms during execution. By capturing how solutions evolve and interact over time, the …

Boosting Chart-To-Code Generation In Mllm Via Dual Preference-Guided Refinement, Zhihan Zhang, Yixin Cao, Lizi Liao

Research Collection School Of Computing and Information Systems

Translating chart images into executable plotting scripts-referred to as the chart-to-code generation task-requires Multimodal Large Language Models (MLLMs) to perform fine-grained visual parsing, precise code synthesis, and robust cross-modal reasoning. However, this task is inherently under-constrained: multiple valid code implementations can produce the same visual chart, and evaluation must consider both code correctness and visual fidelity across diverse dimensions. This makes it difficult to learn accurate and generalizable mappings through standard supervised fine-tuning. To address these challenges, we propose a dual preference-guided refinement framework that combines a feedback-driven, dual-modality reward mechanism with iterative preference learning. Our approach introduces a structured …