Artificial Intelligence and Robotics Commons^™

Revisiting Sentiment Analysis For Software Engineering In The Era Of Large Language Models, Ting Zhang, Ivana Clairine Irsan, Thung Ferdian, David Lo

Research Collection School Of Computing and Information Systems

Software development involves collaborative interactions where stakeholders express opinions across various platforms. Recognizing the sentiments conveyed in these interactions is crucial for the effective development and ongoing maintenance of software systems. For software products, analyzing the sentiment of user feedback, e.g., reviews, comments, and forum posts can provide valuable insights into user satisfaction and areas for improvement. This can guide the development of future updates and features. However, accurately identifying sentiments in software engineering datasets remains challenging.This study investigates bigger large language models (bLLMs) in addressing the labeled data shortage that hampers fine-tuned smaller large language models (sLLMs) in software …

Multi-Uav Reconnaissance Mission Planning Via Deep Reinforcement Learning With Simulated Annealing, Mingfeng Fan, Huan Liu, Guohua Wu, Aldy Gunawan, Guillaume Sartoretti

Research Collection School Of Computing and Information Systems

Unmanned aerial vehicles (UAVs) are widely used in reconnaissance missions due to their autonomy and flexibility. Efficient mission planning for multiple UAVs is crucial for tasks such as traffic monitoring and data collection. However, existing approaches to multi-UAV reconnaissance mission planning problem (MURMPP) often struggle with high computational demands, leading to suboptimal solutions. To overcome this challenge, we introduce a divide-and-conquer framework that splits the problem into two phases: target allocation and UAV routing, effectively reducing computational complexity. Specifically, we propose a hybrid method, SA-NNO-DRL, which combines the nearest neighbor optima-based deep reinforcement learning (NNO-DRL) approach with simulated annealing (SA). …

Multisfl: Towards Accurate Split Federated Learning Via Multi-Model Aggregation And Knowledge Replay, Zeke Xia, Ming Hu, Dengke Yan, Ruixuan Liu, Anran Li, Xiaofei Xie, Mingsong Chen

Research Collection School Of Computing and Information Systems

Although Split Federated Learning (SFL) effectively enables knowledge sharing among resource-constrained clients, it suffers from low training performance due to the neglect of data heterogeneity and catastrophic forgetting problems. To address these issues, we propose a novel SFL approach named MultiSFL, which adopts i) an effective multimodel aggregation mechanism to alleviate gradient divergence caused by heterogeneous data and ii) a novel knowledge replay strategy to deal with the catastrophic forgetting problem. MultiSFL adopts two servers (i.e., the fed server and main server) to maintain multiple branch models for local training and an aggregated master model for knowledge sharing among branch …

Understanding Individual Agent Importance In Multi-Agent System Via Counterfactual Reasoning, Jianming Chen, Yawen Wang, Junjie Wang, Xiaofei Xie, Jun Hu, Qing Wang, Fanjiang Xu

Research Collection School Of Computing and Information Systems

Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has provided explanations for the actions or states of agents, yet falls short in understanding the black-boxed agent's importance within a MAS and the overall team strategy. To bridge this gap, we propose EMAI, a novel agent-level explanation approach that evaluates the individual agent's importance. Inspired by counterfactual reasoning, a larger change in reward caused by the randomized action of agent indicates its higher importance. We model it as a MARL problem to capture interactions across agents. Utilizing counterfactual reasoning, EMAI learns the …

Ragg: Retrieval-Augmented Grasp Generation Model, Zhenhua Tang, Bin Zhu, Yanbin Hao, Chong-Wah Ngo, Richang Hong

Research Collection School Of Computing and Information Systems

Intent-based grasp generation inherently involves challenges such as manipulation ambiguity and modality gaps. To address these, we propose a novel Retrieval-Augmented Grasp Generation model (RAGG). Our key insight is that when humans manipulate new objects, they initially mimic the interaction patterns observed in similar objects, then progressively adjust hand-object contact. Consequently, we develop RAGG as a two-stage approach, encompassing retrieval-guided generation and structurally stable grasp refinement. In the first stage, we propose a Retrieval-Augmented Diffusion Model (ReDim), which identifies the most relevant interaction instance from a knowledge base to explicitly guide grasp generation, thereby mitigating ambiguity and bridging modality gaps …

Aligning Large Language Models For Faithful Integrity Against Opposing Argument, Yong Zhao, Yang Deng, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. However, they can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. To this end, we investigate the problem of maintaining faithful integrity in LLMs. This involves ensuring that LLMs adhere to their faithful statements in the face of opposing arguments and are able to correct their incorrect statements when presented with faithful arguments. In this work, we propose a novel framework, named Alignment for Faithful Integrity with Confidence Estimation (AFICE), which aims to align the LLM responses with faithful integrity. Specifically, …

Dualopt: A Dual Divide-And-Optimize Algorithm For The Large-Scale Traveling Salesman Problem, Shipei Zhou, Yuandong Ding, Chi Zhang, Zhiguang Cao, Yan Jin

Research Collection School Of Computing and Information Systems

This paper proposes a dual divide-and-optimize algorithm (DualOpt) for solving the large-scale traveling salesman problem (TSP). DualOpt combines two complementary strategies to improve both solution quality and computational efficiency. The first strategy is a grid-based divide-and-conquer procedure that partitions the TSP into smaller subproblems, solving them in parallel and iteratively refining the solution by merging nodes and partial routes. The process continues until only one grid remains, yielding a high-quality initial solution. The second strategy involves a path-based divide-and-optimize procedure that further optimizes the solution by dividing it into sub-paths, optimizing each using a neural solver, and merging them back …

Leveraging Constraint Violation Signals For Action Constrained Reinforcement Learning, Janaka Chathuranga Brahmanage, Jiajing Ling, Akshat Kumar

Research Collection School Of Computing and Information Systems

In many RL applications, ensuring an agent’s actions adhere to constraints is crucial for safety. Most previous methods in Action-Constrained Reinforcement Learning (ACRL) employ a projection layer after the policy network to correct the action. However projection-based methods suffer from issues like the zero gradient problem and higher runtime due to the usage of optimization solvers. Recently methods were proposed to train generative models to learn a differentiable mapping between latent variables and feasible actions to address this issue. However, generative models require training using samples from the constrained action space, which itself is challenging. To address such limitations, first, …

Offline Safe Reinforcement Learning Using Trajectory Classification, Ze Gong, Akshat Kumar, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Offline safe reinforcement learning (RL) has emerged as a promising approach for learning safe behaviors without engaging in risky online interactions with the environment. Most existing methods in offline safe RL rely on cost constraints at each time step (derived from global cost constraints) and this can result in either overly conservative policies or violation of safety constraints. In this paper, we propose to learn a policy that generates desirable trajectories and avoids undesirable trajectories. To be specific, we first partition the pre-collected dataset of state-action trajectories into desirable and undesirable subsets. Intuitively, the desirable set contains high reward and …

Occlusion-Insensitive Talking Head Video Generation Via Facelet Compensation, Yuhui Deng, Yuqin Lu, Yangyang Xu, Yongwei Nie, Shengfeng He

Research Collection School Of Computing and Information Systems

Talking head video generation involves animating a still face image using facial motion cues derived from a driving video to replicate target poses and expressions. Traditional methods often rely on the assumption that the relative positions of facial keypoints remain unchanged. However, this assumption fails when keypoints are occluded or when the head is in a profile pose, leading to inconsistencies in identity and blurring in certain facial regions. In this paper, we introduce Occlusion-Insensitive Talking Head Video Generation, a novel approach that eliminates the reliance on spatial correlation of keypoints and instead leverages semantic correlation. Our method transforms facial …

Personamagic: Stage-Regulated High-Fidelity Face Customization With Tandem Equilibrium, Xinzhe Li, Jiahui Zhan, Shengfeng He, Yangyang Xu, Junyu Dong, Huaidong Zhang, Yong Du

Research Collection School Of Computing and Information Systems

Personalized image generation has made significant strides in adapting content to novel concepts. However, a persistent challenge remains: balancing the accurate reconstruction of unseen concepts with the need for editability according to the prompt, especially when dealing with the complex nuances of facial features. In this study, we delve into the temporal dynamics of the text-to-image conditioning process, emphasizing the crucial role of stage partitioning in introducing new concepts. We present PersonaMagic, a stage-regulated generative technique designed for high-fidelity face customization. Using a simple MLP network, our method learns a series of embeddings within a specific timestep interval to capture …

Adversarial Attacks On Event-Based Pedestrian Detectors: A Physical Approach, Guixu Lin, Muyao Niu, Qingtian Zhu, Zhengwei Yin, Zhuoxiao Li, Shengfeng He, Yinqiang Zheng

Research Collection School Of Computing and Information Systems

Event cameras, known for their low latency and high dynamic range, show great potential in pedestrian detection applications. However, while recent research has primarily focused on improving detection accuracy, the robustness of event-based visual models against physical adversarial attacks has received limited attention. For example, adversarial physical objects, such as specific clothing patterns or accessories, can exploit inherent vulnerabilities in these systems, leading to misdetections or misclassifications. This study is the first to explore physical adversarial attacks on event-driven pedestrian detectors, specifically investigating whether certain clothing patterns worn by pedestrians can cause these detectors to fail, effectively rendering them unable …

An Aspect Performance-Aware Hypergraph Neural Network For Review-Based Recommendation, Junrui Liu, Tong Li, Di Wu, Zifang Tang, Yuan Fang, Zhen Yang

Research Collection School Of Computing and Information Systems

Online reviews allow consumers to provide detailed feedback on various aspects of items. Existing methods utilize these aspects to model users' fine-grained preferences for specific item features through graph neural networks. We argue that the performance of items on different aspects is important for making precise recommendations, which has not been taken into account by existing approaches, due to lack of data. In this paper, we propose an aspect performance-aware hypergraph neural network (APH) for the review-based recommendation, which learns the performance of items from the conflicting sentiment polarity of user reviews. Specifically, APH comprehensively models the relationships among users, …

Marginal Benefit Driven Rl Teacher For Unsupervised Environment Design, Dexun Li, Wenjun Li, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Training generally capable agents in complex environments is a challenging task that involves identifying the “right” environments at the training stage. Recent research has highlighted the potential of the Unsupervised Environment Design framework, which generates environment instances/levels adaptively at the frontier of the agent’s capabilities using regret measures. While regret approaches have shown promise in generating feasible environments, they can produce difficult environments that are challenging for an RL agent to learn from. This is because regret represents the best-case (upper bound) learning potential and not the actual learning potential of an environment. To address this, we propose an alternative …

Simulation-Free Hierarchical Latent Policy Planning For Proactive Dialogues, Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Yiheng Sun, Zerui Chen, Ming Liu, Bing Qin

Research Collection School Of Computing and Information Systems

Recent advancements in proactive dialogues have garnered significant attention, particularly for more complex objectives (e.g. emotion support and persuasion). Unlike traditional task-oriented dialogues, proactive dialogues demand advanced policy planning and adaptability, requiring rich scenarios and comprehensive policy repositories to develop such systems. However, existing approaches tend to rely on Large Language Models (LLMs) for user simulation and online learning, leading to biases that diverge from realistic scenarios and result in suboptimal efficiency. Moreover, these methods depend on manually defined, context-independent, coarse-grained policies, which not only incur high expert costs but also raise concerns regarding their completeness. In our work, we …

Adapting Knowledge Prompt Tuning For Enhanced Automated Program Repair, Xuemeng Cai, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Automated Program Repair (APR) aims to enhance software reliability by automatically generating bug-fixing patches. Recent work has improved the state-of-the-art of APR by fine-tuning pre-trained large language models (LLMs), such as CodeT5, for APR. However, the effectiveness of fine-tuning be-comes weakened in data scarcity scenarios, and data scarcity can be a common issue in practice, limiting fine-tuning performance. To alleviate this limitation, this paper adapts prompt tuning for enhanced APR and conducts a comprehensive study to evaluate its effectiveness in data scarcity scenarios, using three LLMs of different sizes and six diverse datasets across four programming languages. Prompt tuning rewrites …

Evaluating Software Development Agents: Patch Patterns, Code Quality, And Issue Complexity In Real-World Github Scenarios, Zhi Chen, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

In recent years, AI-based software engineering has progressed from pre-trained models to advanced agentic workflows, with Software Development Agents representing the next major leap. These agents, capable of reasoning, planning, and interacting with external environments, offer promising solutions to complex software engineering tasks. However, while much research has evaluated code generated by large language models (LLMs), comprehensive studies on agent-generated patches, particularly in real-world settings, are lacking. This study addresses that gap by evaluating 4,892 patches from 10 top-ranked agents on 500 real-world GitHub issues from SWE-Bench Verified, focusing on their impact on code quality. Our analysis shows no single …

Drone Delivery Network Design With Uncertainties, Wenjia Zeng, Jiang Ruiwei, Hai Yang, Hai Wang

Research Collection School Of Computing and Information Systems

Unmanned aerial vehicles (UAVs), also called drones, are gaining popularity as an alternative delivery mode due to their faster delivery speed and reduced labor costs. Several companies, especially e-commerce giants, are conducting pilot projects that use drones to deliver fast food and groceries. In 2021, for example, Walmart partnered with Zipline in the United States to provide delivery services for areas near Walmart stores in Arkansas. In China, Meituan drone delivery services have been launched in Shenzhen and have conducted trial food delivery that cover more than 8,000 households.

Unlocking The Potential Of Black-Box Pre-Trained Gnns For Graph Few-Shot Learning, Qiannan Zhang, Shichao Pei, Yuan Fang, Xiangliang Zhang

Research Collection School Of Computing and Information Systems

Few-shot learning has emerged as an important problem on graphs to combat label scarcity, which can be approached by current trends in pre-trained graph neural networks (GNNs) and meta-learning. Recent efforts integrate both paradigms in a white-box setting, leaving the more realistic black-box setting largely underexplored, where the parameters and gradients in the pre-trained GNNs are inaccessible. In this paper, we study the critical problem: Leveraging black-box pre-trained GNNs for graph few-shot learning. Despite its appeal, two key issues hinder the unlocking of its potential: the inherent task gap between pre-training and downstream stages, which can introduce irrelevant knowledge and …

Learning To Identify Seen, Unseen And Unknown In The Open World: A Practical Setting For Zero-Shot Learning, Sethupathy Parameswaran, Yuan Fang, Chandan Gautam, Savitha Ramasamy, Xiaoli Li

Research Collection School Of Computing and Information Systems

As vision-language models advance, addressing the Zero-Shot Learning (ZSL) problem in the open world becomes increasingly crucial. Specifically, a robust model must handle three types of samples during inference: seen classes with visual and semantic information provided in training, unseen classes with only the semantic information in training, and unknown samples with no prior information from training. Existing methods either handle seen and unseen classes together (ZSL) or seen and unknown classes (known as Open-Set Recognition, OSR). However, none addresses the simultaneous handling of all three, which we term Open-Set Zero-Shot Learning (OZSL). To address this problem, we propose a …

Dr. Tongue: Sign-Oriented Multi-Label Detection For Remote Tongue Diagnosis, Yiliang Chen, Steven S. C. Ho, Cheng Xu, Yao Jie Xie, Wing Fai Yeung, Shengfeng He, Jing Qin

Research Collection School Of Computing and Information Systems

Tongue diagnosis is a vital tool in Western and Traditional Chinese Medicine, providing key insights into a patient's health by analyzing tongue attributes. The COVID-19 pandemic has heightened the need for accurate remote medical assessments, emphasizing the importance of precise tongue attribute recognition via telehealth. To address this, we propose a Sign-Oriented multi-label Attributes Detection framework. Our approach begins with an adaptive tongue feature extraction module that standardizes tongue images and mitigates environmental factors. This is followed by a Sign-oriented Network (SignNet) that identifies specific tongue attributes, emulating the diagnostic process of experienced practitioners and enabling comprehensive health evaluations. To …

Quantifying The Role Of Active Listening And Reassurance In Virtual Health Coach Interactions, Ghulam Hussain, Brian Keegan, Robert Ross

Conference papers

Conversational Agents have the potential to support healthcare through coaching exercise routines, but are still lacking in demonstrating authentic social behaviours to support engagement. To this end, we present a series of experiments that we conducted in order to investigate how automated health care coaches can be more effective when their interaction style is tailored to demonstrate qualities associated with a good bedside manner, namely active listening and reassurance. To test this, we first developed a dataset of 135 dialogue excerpts from three distinct sources, i.e., original, handcrafted and LLMs, the latter two of which were tuned to demonstrate specific …

Patient Consent And The Right To Notice And Explanation Of Ai Systems Used In Health Care, Meghan E Hurley, Benjamin H Lang, Kristin Marie Kostick-Quenet, Jared N Smith, Jennifer Blumenthal-Barby

Center for Medical Ethics and Health Policy Staff Publications

Given the need for enforceable guardrails for artificial intelligence (AI) that protect the public and allow for innovation, the U.S. Government recently issued a Blueprint for an AI Bill of Rights which outlines five principles of safe AI design, use, and implementation. One in particular, the right to notice and explanation, requires accurately informing the public about the use of AI that impacts them in ways that are easy to understand. Yet, in the healthcare setting, it is unclear what goal the right to notice and explanation serves, and the moral importance of patient-level disclosure. We propose three normative functions …

Smart Highway Construction Site Monitoring Using Artificial Intelligence, Mehran Mazari, Yahaira Nava-Gonzalez, Ly Jacky N. Nhiayi, Mohamad H. Saleh

Mineta Transportation Institute

Construction is a large sector of the economy and plays a significant role in creating economic growth and national development,and construction of transportation infrastructure is critical. This project developed a method to detect, classify, monitor, and track objects during the construction, maintenance, and rehabilitation of transportation infrastructure by using artificial intelligence and a deep learning approach. This study evaluated the performance of AI and deep learning algorithms to compare their performance in detecting and classifying the equipment in various construction scenes. Our goal was to find the optimized balance between the model capabilities in object detection and memory processing requirements. …

Enhancing Virtual Reality Usability With A Ml Based Dynamic Adaptive System, Ananth Ramaseri-Chandra, Hassan Reza

Computer Science Posters and Presentations

Virtual reality (VR) holds tremendous potential, but cybersickness degrades the user experience. Since individuals vary, a one-size-fits-all design is insufficient. Our work introduces a dynamic adaptive system that personalizes VR experiences by learning individual cybersickness profiles from head-tracking data and sickness questionnaires while adjusting settings such as field of view and foveated rendering strength. Early results show that our system reduces post-exposure sickness scores, enhancing the user experience and highlighting the importance of personalizing VR.

What's The Art In Artificial Intelligence?, Emily Verla Bovino

Open Educational Resources

This workbook learns from Black and Indigenous artists working with Artificial Intelligence to confront issues of ethics and aesthetics in its technologies. It features guided learning activities with links to publicly available video lectures and online articles, and includes options for experiential learning through both a tutorial in Midjourney and a visit to the public art collection at York College in Jamaica, Queens. Featured artists include: American Artist, Rizvana Bradley, Beth Coleman, Denise Ferreira da Silva, Suzanne Kite, Sondra Perry, Mimi Onuoha and Alisha B. Wormsley. Works by Martin Puryear and Maren Hassinger are explored in the Midjourney exercise.

About …

Human-Ai Collaboration In Writing: A Multidimensional Framework For Creative And Intellectual Authorship, James Hutson

Faculty Scholarship

The integration of AI technologies into the writing process has significantly altered traditional notions of authorship, creativity, and intellectual labor. Historically, writing was seen as a human-driven cognitive and creative exercise, but with the rise of generative AI tools such as ChatGPT and Claude, the line between human and AI contributions has become increasingly ambiguous. This paper addresses the limitations of the current sliding scale model, which views AI involvement as ranging from “none” to “complete”. In its place, we propose a new multidimensional framework that more accurately reflects the complexity of human-AI collaboration in writing. The model includes axes …

Beyond The Blue Skies: A Comprehensive Guide For Risk Assessment In Aviation, Leila Halawi, Mark Miller, Sam Holley

Publications

Risk assessment in aviation is a critical process that safeguards the safety and reliability of operations. Aviation operations encompass inherent risks, from mechanical failures to human errors and environmental factors. The significance of these risks may be severe, leading to accidents, injuries, and loss of life. Recognizing and mitigating risks is supreme in this dynamic environment, where emerging technologies and innovation constantly reshape this industry. This chapter includes an in-depth explanation of risk management and analysis, leading to the core elements of risk assessment specifically for aviation operations. We will describe the process and explore some of the applications and …

Using Ai To Make Accessible Accessible Content, Melinda Turner

Faculty Other Scholarly Works

This professional development session will explore how to leverage AI tools, specifically Google’s NotebookLM, to create accessible learning materials for college students. Participants will learn how to use NotebookLM to transform existing content into more accessible formats. The session will cover practical strategies for implementing AI to improve readability and comprehension for all learners including students with disabilities, non-native English speakers, and students with varying learning preferences. We will discuss how to create transcripts for audio/video files and ensure content is well-organized and easy to navigate. This session will also highlight the importance of evidence-based practices in content creation and …

A Review Of Racial Differences And Disparities In Ecg, Jianwei Zheng, Chizobam Ani, Islam Abudayyeh, Yunfan Zheng, Cyril Rakovski, Ehsan Yaghmaei, Omolola Ogunyemi

Mathematics, Physics, and Computer Science Faculty Articles and Research

The electrocardiogram (ECG) is a widely used, non-invasive tool for diagnosing a range of cardiovascular conditions, including arrhythmia and heart disease-related structural changes. Despite its critical role in clinical care, racial and ethnic differences in ECG readings are often underexplored or inadequately addressed in research. Variations in key ECG parameters, such as PR interval, QRS duration, QT interval, and T-wave morphology, have been noted across different racial groups. However, the limited research in this area has hindered the development of diagnostic criteria that account for these differences, potentially contributing to healthcare disparities, as ECG interpretation algorithms largely developed from major …