Artificial Intelligence and Robotics Commons^™

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

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 …

Sequential Robustness In Adversarial Reinforcement Learning, Roman Lok-Ming Belaire

Dissertations and Theses Collection (Open Access)

My goal is to build autonomous systems that expand the reach of human capability in challenging domains such as undersea and space exploration, disaster response, and large-scale infrastructure. In everyday settings, these systems will increasingly appear in safety-critical applications such as autonomous driving, robotics, and industrial manufacturing. A central requirement for these systems is the ability to operate reliably under uncertainty, particularly when the environment behaves in unanticipated ways.

The robust handling of unforeseen environment dynamics is therefore a technical cornerstone of autonomous decision-making; Adversarial attacks provide a useful and principled lens through which to study this problem. Adversarial \textit{robustness}, …

Perspectives On Interpretability For Neural Text Representations, Jia Peng Lim

Dissertations and Theses Collection (Open Access)

In this dissertation, we investigate interpretability in the three elements of learning neural text representations: inputs, passed into models, to produce probabilistic outputs. We emphasise perspectives as we present alternative novel methods to mine and organise meaning in this work.

Models. We initiate our investigation by examining Neural Topic Models (NTM), proposing an alternate angle of interpreting its word-topic distribution, producing better topic representations for interpretation. Our method maps the problem of finding these better interpretations to classical NP-hard graph problems, enabling examination of topic distributions in a composite manner. Next, we apply our previous findings to extract interpretations from …

Generative Ai In Enterprises: Optimizing Applications With Large Language Models, Donghao Huang

Dissertations and Theses Collection (Open Access)

This dissertation investigates how to deploy Large Language Models (LLMs) effectively in enterprise settings, where accuracy, reliability, cost, privacy, and operational constraints often matter more than benchmark performance alone. Drawing on seventeen peer-reviewed publications (eleven published and six accepted for publication), the work develops and validates optimization strategies across three connected themes: retrieval-augmented generation (RAG), agentic AI for workflow automation, and deployment guidelines for real-world enterprise environments.

First, we study RAG optimization through systematic evaluation of open and proprietary models, highlighting conditions under which efficient open-weight models can match or exceed proprietary alternatives. To address a pervasive failure mode in …

Optimizing And Fortifying Ai Software Through The Lens Of Artifact Synthesis, Jieke Shi

Dissertations and Theses Collection (Open Access)

Artificial Intelligence (AI) has transformed the software landscape, ushering in a new era of intelligent systems that increasingly shape our daily lives. This transformation is evident in various domains, including Software Engineering (SE), where Large Language Models (LLMs) support many development tools, and control systems, where self-driving cars and autonomous drones rely on deep learning models for real-time decision-making. These AI systems are collectively referred to as AI software, with the former categorized as AI4SE software (AI for Software Engineering) and the latter as AI4Control software (AI for Control). As AI software becomes central to modern computing infrastructure, its reliability …

Inside Out: Improving Large Model Safety, Wei Zhao

Dissertations and Theses Collection (Open Access)

While Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) are at the frontier of current advancements in artificial intelligence, demonstrating remarkable capabilities across diverse applications, there are growing concerns about their reliability and security. LLMs remain vulnerable to adversarial attacks through carefully crafted prompts that circumvent safety mechanisms, while MLLMs face additional security challenges stemming from their multimodal nature. Despite considerable efforts in reinforcement learning from human feedback (RLHF) and supervised fine-tuning, existing safeguards have proven inadequate in addressing these critical vulnerabilities. This inadequacy stems from the fact that these models are inherently blackboxes that do not provide …

Constrained Reinforcement Learning: From Single-Agent Safety To Multi-Agent Coordination, Hao Jiang

Dissertations and Theses Collection (Open Access)

Real-world decision-making systems such as autonomous driving and largescale ride-pooling must operate under strict safety and resource constraints. Traditional Reinforcement Learning (RL) methods, while powerful in simulation, often fail to guarantee such constraints, limiting their real-world deployment. The fundamental challenge lies in integrating constraint satisfaction with long-term reward optimization, especially when outcomes are stochastic and interdependent across multiple agents.

This dissertation advances the field of Constrained Reinforcement Learning (CRL) from both single-agent safety and multi-agent coordination perspectives. In the single-agent setting, we introduce a Reward Penalty framework that augments the state space with cumulative cost and penalizes only trajectories that …

Graph Perturbations For Robust Knowledge Discovery And Retrieval, Hanhua Xiao

Dissertations and Theses Collection (Open Access)

Graph perturbation, rooted in classical perturbation theory, studies how small topology edits, i.e., adding or deleting edges, affects graph properties (e.g., density, centrality). This fundamental problem underpins applications like bioinformatics, privacy preservation and system defense. While much prior work targets perturbations that influence global graph statistics or model outputs, comparatively little addresses robustness for knowledge discovery and information retrieval. In these settings, graphs are attributed: nodes carry real-world semantics (e.g., locations, people) and edges encode interactions or relationships. This thesis proposes new formulations and algorithms that generate and leverage graph perturbations to make knowledge discovery and retrieval more robust. Specifically, …

Enhancing Multi-View, Multi-Modal Sensing, Perception And Actuation For Edge Intelligence, Dhanuja Tharith Wanniarachchige

Dissertations and Theses Collection (Open Access)

Artificial Intelligence of Things (AIoT) technologies have ushered in exciting new advances in intelligent sensing, perception, and actuation for many real-world cyberphysical systems (CPS) applications. These technologies have had a formidable impact in domains such as large-scale video surveillance, autonomous transportation and robotics, precision healthcare, and industrial automation. In these applications, sensors and actuators are often collocated with processing nodes, and such nodes are typically interconnected via wireless networks. Vision-based machine intelligence, exemplified by tasks such as object detection, object tracking, and activity analysis, is a very common enabler of such CPS applications. Efficient execution of Deep Neural Network (DNN) …

Scaling Up Cooperative Multi-Agent Reinforcement Learning, Minghong Geng

Dissertations and Theses Collection (Open Access)

Multi-agent systems (MAS) involve multiple autonomous agents that coordinate their actions to achieve shared or competing objectives in dynamic environments. Over the past decade, multi-agent reinforcement learning (MARL) has emerged as a powerful paradigm for enabling collaborative behaviors among autonomous agents within MAS to solve complex tasks. This dissertation discusses a critical scalability gap that exists between current MARL capabilities and real-world deployment requirements. Most existing MARL research focuses on small-scale laboratory problems, often struggling to coordinate large agent populations and facing challenges with extended decision-making horizons. In contrast, many real-world applications demand coordination among hundreds or thousands of agents …

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, …

Machine Learning For Digital Biomarker-Based Detection Of Cognitive Decline, Seng Khoon The

Dissertations and Theses Collection (Open Access)

Dementia is a neurodegenerative disease with a prevalence rate expected to triple by 2050, posing a significant challenge for health services. To impede the increasing prevalence, medical professionals and scientists are actively investigating technology to detect cognitive decline at a reversible stage known as Mild Cognitive Impairment (MCI). Digital biomarker technology is an emerging pragmatic approach to permit objective, ecologically valid, and long-term continuous measurement of cognitive health status, rendering it as one of the promising technologies for early MCI detection. Despite its potential, it is nontrivial to encode, extract and combine predictive information from these digital biomarker technologies; advanced …

From Sparse Feedback To Sequential Decision-Making: Learning Safety Constraints With Weak Supervision, Siow Meng Low

Dissertations and Theses Collection (Open Access)

Real-world decision-making often involves safety constraints that are implicit, non-Markovian, or difficult to specify directly. Standard reinforcement learning (RL) approaches typically assume access to fully specified cost functions and constraint budgets—assumptions that limit their applicability in domains where such structure must instead be inferred from data. This dissertation develops a sequence of methods for learning safety-relevant structure from weak supervision, such as sparse binary feedback on trajectory segments, and using these signals to guide planning and policy optimization.

The first part of the dissertation introduces a sample-efficient method for planning in continuous Markov Decision Processes (MDPs) using deep reactive policies. …

Cutting Through The Infodemic Efficiently: News Claims Surveillance And Llm-Based Lightweight Fact Verification, Xuan Zhang

Dissertations and Theses Collection (Open Access)

In the context of the current infodemic, the rapid spread of misinformation poses a severe threat to social stability and public health. Recently, the rise of deep learning technologies has offered the potential for accelerating the development of automated misinformation detection and verification. However, current technological capabilities and computational resources often prove inadequate for the exhaustive scrutiny required, rendering the enhancement of processing efficiency a critical imperative. Given the vast amount of data on the internet, current technology and computational power often fall short in timely and accurate scrutiny of each piece of information, making the improvement of processing efficiency …

Rich Models And Methods For On-Demand Same Day Deliveries, Zhiqin Zhang

Dissertations and Theses Collection (Open Access)

Same-day delivery has brought numerous conveniences to people’s lives, but it has also presented challenges in terms of service management. To effectively optimize on-demand same-day delivery operations within urban logistics, intelligent decision-making strategies capable of adapting to rapidly changing circumstances are essential. Employing effective decisionmaking strategies that account for order allocation, route planning, courier scheduling, and other relevant factors, is pivotal in advancing logistics operations, enhancing efficiency, customer satisfaction, and resource utilization in the context of dynamic same-day delivery problems.

The focus of this thesis revolves around different emerging challenges presented by on-demand same-day delivery problems, with a particular emphasis …

Interactive Generative Modeling: A Pathway For Improved Simulation And Decision Making, Changyu Chen

Dissertations and Theses Collection (Open Access)

This dissertation presents Interactive Generative Modeling (IGM), a unified perspective that integrates interactive paradigm and generative modeling to advance the development of general-purpose intelligent systems. IGM is motivated by the observation that while reinforcement learning (RL) has mastered a wide range of complex simulated tasks, it struggles to generalize in high-dimensional, open-ended tasks. In contrast, generative models excel in such settings due to their expressivity and their ability to serve as powerful priors (e.g., LLMs pretrained on massive corpora). By bridging these two paradigms, IGM offers a promising path forward.

The first direction explored in this dissertation is IGM for …

Learning And Optimization Under Human-Centric Considerations, Qian Shao

Dissertations and Theses Collection (Open Access)

This dissertation investigates learning and optimization problems shaped by humancentric considerations, such as preferences, demonstrations, behavioral patterns, and resource constraints. As real-world decision-making increasingly involves interaction with human agents, data, and limitations, modeling these factors becomes critical for building practical, adaptive, and robust systems.

The research spans four domains. First, we study preference-aware delivery routing by learning implicit practitioner preferences and incorporating them into a hierarchical route optimization framework. Second, we develop imitation learning methods for cost-constrained settings, enabling agents to mimic expert behavior while respecting safety and resource limitations. Third,we explore early rumor detection in data-limited environments, integrating large …

Generative Artificial Intelligence Dependency: Scale Development, Validation, And Its Motivational, Behavioral, And Psychological Correlates, Adalia Yin Hui Goh

Dissertations and Theses Collection (Open Access)

The growing integration of generative artificial intelligence (AI) into everyday life has raised questions about its potential psychological and behavioral consequences. The present research develops and validates the Generative AI Dependency Scale, a multidimensional tool developed to assess individual differences in dependency on generative AI systems. Across six studies involving 1,223 participants from the United States and Singapore, the Generative AI Dependency Scale demonstrated strong psychometric properties, including a stable three-factor structure (cognitive preoccupation, negative consequences, withdrawal) and good test-retest reliability (ICC = .85). Confirmatory factor analysis supported a higher-order dependency construct, and scalar measurement invariance was established across sex …

Diversity-Augmented Training For Generalizable Ai Agents, Wenjun Li

Dissertations and Theses Collection (Open Access)

Deep Reinforcement Learning (RL) has achieved remarkable success over the past decade, from superhuman performance in video games to real-world applications like robotics. However, RL models often lack generalization, making them unreliable when deployed in unfamiliar scenarios. For example, robots must adapt to varying terrains with different slopes and obstacles, yet standard RL training does not explicitly promote such adaptability. While various methods have been proposed to enhance RL robustness, achieving reliable generalization remains an open challenge.

This dissertation focuses on improving the generalization capability of agents in three major settings: infinite horizon RL agents, finite horizon RL agents, and …

Towards Reliable Ml: Data Attribution And Adversarial Robustness, Xiaosen Zheng

Dissertations and Theses Collection (Open Access)

Modern machine learning (ML) models achieve remarkable success, but face critical reliability challenges. This thesis advances two pillars of reliable ML systems: interpretability through data attribution and robustness against adversarial threats.

In the first part, we develop novel data attribution methods to elucidate the data-model relationship. We establish the critical role of memorization in model generalization through token-level influence analysis, extend sample-level attribution to diffusion models with effective approximation techniques, and introduce REGMIX, a group-level approach that predicts data mixture performance using small-scale experiments. These contributions provide practitioners with scalable tools to audit training data impacts across modalities.

The second …

Disentangling User Preferences Towards Self-Interpretable Recommender Systems, Nhu Thuat Tran

Dissertations and Theses Collection (Open Access)

Understanding user preferences remains a central challenge in recommender systems due to their inherently complex, unstructured, and multi-faceted nature, exacerbated by the sparsity of user interaction data. Traditional approaches often compress user interests into a single latent vector, overlooking the fact that user preferences are typically shaped by multiple underlying factors that differ across individuals. These latent drivers are not directly observable and must be discovered through unsupervised modeling, further complicated by limited historical interactions per user.

This dissertation addresses these challenges by introducing a principled framework for multiinterest modeling, which disentangles user behaviors into multiple latent factors to better …

The Impact Of Ai Usage On Employee Work Outcomes: The Mediating Roles Of Personal Control And Job Insecurity And The Moderating Role Of Ai Trust, Tiantian Wang

Dissertations and Theses Collection (Open Access)

The widespread application of artificial intelligence (AI) technology in the workplace offers significant potential for process optimization andperformance improvement. However, the psychological mechanisms throughwhich AI usage affects employee outcomes remain underexplored. To address this gap, the present study investigated a sample of 170 employees froma media company in China, utilizing a three-wave longitudinal survey design. Specifically, this study examined how AI usage influenced employee creativity and task performance improvement through two mediatingmechanisms: the enhancement of personal control in problem-solving and the elicitation of job insecurity. Furthermore, the moderating role of trust in AI inthe relationship between AI usage and job …

Exploring Intelligent Manufacturing: How Artificial Intelligence Affects Productivity And Labor Demand At The Enterprise Level, Jie Gu

Dissertations and Theses Collection (Open Access)

Manufacturing is a cornerstone of national economic health and social stability, yet it faces challenges such as declining profits, rising labor costs, and an aging workforce. In China, the manufacturing sector is undergoing a critical transformation, driven by technological advancements like artificial intelligence (AI) and the push for intelligent manufacturing. This study explores how AI revitalizes the manufacturing sector by enhancing enterprise productivity and reshaping labor demand, with a focus on quality inspection processes. Using a leading bearing factory as a case study, the research employs econometric models, A/B testing, and interviews to quantify AI’s impact on production efficiency, costs, …

Robust Learning With Probabilistic Relaxation Using Hypothesis-Test-Based Sampling, Zilin Wang

Dissertations and Theses Collection (Open Access)

In recent years, deep learning has been a vital tool in various tasks. The performance of a neural network is usually evaluated by empirical risk minimization. However, robustness issues have gained great concern which can be fatal in safety-critical applications. Adversarial training can mitigate the issue by minimizing the loss of worst-case perturbations of data. It is effective in improving the robustness of the model, but it is too conservative, and the plain performance of the model can be unsatisfying. Probabilistic Robust Learning (PRL) empirically balances the average- and worst-case performance while the robustness of the model is not provable …

Ai And Creativity: Effects Of Culture And Task Emotiveness In Human-Ai Collaboration, Choon Ngee Tan

Dissertations and Theses Collection (Open Access)

Creativity is the driving force behind innovation, propelling individuals and societies toward progress by generating novel ideas and groundbreaking solutions. The emergence of generative AI models, exemplified by GPT-3, offers opportunities to enhance human creativity. This paper explores the potential for unprecedented breakthroughs through the synergy between human intuition and AI-driven creativity, providing practical guidance on leveraging AI to amplify creative capacities. Study 1 finds that AI models trained on data from the U.S. and Chinese cultures exhibit cultural norms, values and cognition of those cultures. Study 2 finds that when humans and AI models of the same culture collaborate …

Food Computing: Domain Adaptation And Causal Inference, Qing Wang

Dissertations and Theses Collection (Open Access)

This dissertation addresses two challenges in food computing: food recognition and food image-to-recipe retrieval. The main research ideas are: (1) leveraging Large Language Models (LLMs) to augment food image representations to mitigate the combined challenges of domain gaps and data imbalance in fine-grained food recognition; (2) proposing a causal-theory inspired cross-modal representation learning formulation for reducing the bias caused by the emphasis on certain ingredients for cross-modal recipe retrieval; and (3) extending the framework to incorporate multiple confounding factors, particularly ingredients and cooking actions, allows for more comprehensive modeling of the food image-torecipe retrieval problem.

We first explore the challenges …

Influence Of Artificial Intelligence (Ai) On Decision-Making For Market-Entry Strategies In Emerging Economies, Tejas Deshpande

Dissertations and Theses Collection (Open Access)

International firms with growth-oriented business models face a complex array of factors when planning to enter emerging markets. These markets are characterized by dynamic socio-economic and geopolitical conditions, often resulting in limited market intelligence and a fragmented understanding of the business ecosystem. To succeed, firms must align their short-term objectives and long-term strategic goals with the specific characteristics of these target markets.

Decision-making in such environments is fraught with uncertainty and is critical in determining the success or failure of market-entry strategies. While business leaders rely on their cognition and heuristics to navigate these challenges, the complexity and volume of …

The Impact Of Instrumental Attribution In Ai-Enabled Monitoring On Counterproductive Work Behavior, Qiang Zhang

Dissertations and Theses Collection (Open Access)

AI-enabled monitoring tools are theoretically expected to suppress unethical employee behavior. However, in practice, employees may perceive such monitoring as being driven by leaders' instrumental motives, primarily focused on personal performance evaluation and self-interest. This perception can foster feelings of job insecurity and moral disengagement, ultimately leading to counterproductive work behavior (CWB), which includes unethical employee behavior and turnover. These outcomes may undermine the intended effectiveness of AI-enabled monitoring tools. This study aims to explore the impact of Instrumental Attribution in AIenabled Monitoring (IAAIM) on CWB, specifically focusing on unethical employee behavior and turnover, through both theoretical and empirical lenses. …

Multi-Modal Alignment Via Hyperbolic Geometry, Suyu Liu

Dissertations and Theses Collection (Open Access)

Strong capabilities of generalization to unseen domains are vital for deep neural networks. While existing methods have shown promising results without source domain access, they mostly rely on models that are extensively pre-trained on source domains or overlook the intricate hierarchical structures inherent in visual and textual features. These limitations may have bad impacts on performances, especially on datasets with many classes. To overcome this, in this paper we propose a novel approach that projects the model onto hyperbolic geometry and employs geometric optimal transport to align cross-modal features in an unsupervised manner. Unlike Euclidean geometry, hyperbolic geometry is characterized …