Artificial Intelligence and Robotics Commons^™

Loco: Low-Bit Communication Adaptor For Large-Scale Model Training, Xingyu Xie, Zhijie Lin, Kim-Chuan Toh, Pan Zhou

Research Collection School Of Computing and Information Systems

To efficiently train large-scale models, low-bit gradient communication compresses full-precision gradients on local GPU nodes into low-precision ones for higher gradient synchronization efficiency among GPU nodes. However, it often degrades training quality due to compression information loss. To address this, we propose the Low-bit Communication Adaptor (LoCo), which compensates gradients on local GPU nodes before compression, ensuring efficient synchronization without compromising training quality. Specifically, LoCo designs a moving average of historical compensation errors to stably estimate concurrent compression error and then adopts it to compensate for the concurrent gradient compression, yielding a less lossless compression. This mechanism allows it to …

A Causality-Aware Paradigm For Evaluating Creativity Of Multimodal Large Language Models, Zhongzhan Huang, Shanshan Zhong, Pan Zhou, Shanghua Gao, Marink Zitnik, Liang Lin

Research Collection School Of Computing and Information Systems

Recently, numerous benchmarks have been developed to evaluate the logical reasoning abilities of large language models (LLMs). However, assessing the equally important creative capabilities of LLMs is challenging due to the subjective, diverse, and data-scarce nature of creativity, especially in multimodal scenarios. In this paper, we consider the comprehensive pipeline for evaluating the creativity of multimodal LLMs, with a focus on suitable evaluation platforms and methodologies. First, we find the Oogiri game—a creativity-driven task requiring humor, associative thinking, and the ability to produce unexpected responses to text, images, or both. This game aligns well with the input-output structure of modern …

Human‑Ai And Human‑Robot Collaboration In The Age Of Generative Ai, Agentic Ai, And Artificial General Intelligence: Opportunities And Challenges, Keng Siau

Research Collection School Of Computing and Information Systems

The advancement of Artificial Intelligence (AI) has been exponential, especially in the past few years. Most, if not all, of the AI systems we encounter and are exposed to at this point are Artificial Narrow Intelligence (ANI). ANI specializes in one area and solves problems in one area. Generative AI (GenAI) and Agentic AI (i.e., independent AI agent), at the current stage of development, are regarded as ANI. The race is currently on to develop Artificial General Intelligence (AGI). AGI refers to AI systems as smart as humans across a wide range of cognitive tasks. Recently, OpenAI’s o3 system received …

Seven Hci Grand Challenges Revisited: Five-Year Progress, Constantine Stephanidis, Gavriel Salvendy, Margherita Antona, Vincent G Duffy, Qin Gao, Waldemar Karwowski, Fiona Nah, Stavroula Ntoa, Pei-Luen Patrick Rau, Keng Siau, Jia Zhou

Research Collection School Of Computing and Information Systems

Motivated by the rapid technological advancements achieved in the last five years, and the pervasiveness of Artificial Intelligence, the paper investigates the evolving role of Human-Computer Interaction and revisits the seven grand challenges outlined in 2019: human-technology symbiosis, human-environment interactions, ethics, privacy and security, well-being, health and eudaimonia, accessibility and universal access, learning and creativity, and social organization and democracy. Through literature analysis, the paper reevaluates the status of each challenge and highlights emerging requirements. Key findings reveal the widespread impact of Artificial Intelligence across all domains and emphasize the need for improved AI transparency, alignment with human values, and …

Hotpatching On The Fly: Mitigating Drone Incidents Arising From Incorrect Configuration, Ruidong Han, Juanru Li, Zhuo Ma, David Lo, Arash Shaghaghi, Jianfeng Ma, Siqi Ma

Research Collection School Of Computing and Information Systems

Manufacturers offer adjustable control parameters for flight control systems to accommodate diverse environments and missions. To ensure flight safety, they also develop established boundaries, i.e., range specifications for parameter values. However, even when the configuration parameters fall within the prescribed manufacturer range, they could still lead to instability or even severe incidents like crashes, which are referred to as Range Specification Bugs. Prior research has suggested shrinking the range of parameter values to protect drones from the adverse effects of such bugs. However, narrowing the range of parameters may only reduce the probability of errors and could potentially limit the …

Ai As Your Ally: The Effects Of Ai-Assisted Venting On Negative Affect And Perceived Social Support, Meilan Hu, Xavier Cheng Wee Chua, Shu Fen Diong, K. T. A. Sandeeshwara Kasturiratna, Nadyanna M. Majeed, Andree Hartanto

Research Collection School of Social Sciences

In recent years, artificial intelligence (AI) chatbots have made significant strides in generating human-like conversations. With AI's expanding capabilities in mimicking human interactions, its affordability and accessibility underscore the potential of AI chatbots to facilitate negative emotional disclosure or venting. The study's primary objective is to highlight the potential benefits of AI-assisted venting by comparing its effectiveness to venting through a traditional journaling platform in reducing negative affect and increasing perceived social support. We conducted a pre-registered within-subject experiment involving 150 participants who completed both traditional venting and AI-assisted venting conditions with counterbalancing and a wash-out period of 1-week between …

Vaxbot-Hpv: A Gpt-Based Chatbot For Answering Hpv Vaccine-Related Questions, Yiming Li, Jianfu Li, Manqi Li, Evan Yu, Danniel Rhee, Muhammad Amith, Lu Tang, Lara S Savas, Licong Cui, Cui Tao

Faculty, Staff and Student Publications

OBJECTIVE: Human Papillomavirus (HPV) vaccine is an effective measure to prevent and control the diseases caused by HPV. However, widespread misinformation and vaccine hesitancy remain significant barriers to its uptake. This study focuses on the development of VaxBot-HPV, a chatbot aimed at improving health literacy and promoting vaccination uptake by providing information and answering questions about the HPV vaccine.

METHODS: We constructed the knowledge base (KB) for VaxBot-HPV, which consists of 451 documents from biomedical literature and web sources on the HPV vaccine. We extracted 202 question-answer pairs from the KB and 39 questions generated by GPT-4 for training and …

Negotiating With Gpt-4: Digital Doormat Or Skilful Counterpart?, Dorcas Quek Anderson

Research Collection Yong Pung How School Of Law

Large language models (LLMs) such as GPT-4 have been creatively harnessed in the conflict resolution arena as dialogue agents interacting with humans within negotiations, due to their capacity for in-context learning and giving human-like responses. In light of the burgeoning use of LLMs in conflict resolution training, a pilot study was conducted to ascertain the desirability of using dialogue agents built on GPT-4 in conducting simulations for students learning negotiation skills. This article discusses insights gained from the study on the reliability of LLM agents in following prompts for negotiation simulations; notable negotiation behaviour of the LLM agent; the degree …

Towards The Next Generation Of Geospatial Artificial Intelligence, Gengchen Mai, Yiqun Xie, Xiaowei Jia, Ni Lao, Jinmeng Rao, Qing Zhu, Zeping Liu, Yao-Yi Chiang, Jiao, Junfeng

Research Collection College of Integrative Studies

Geospatial Artificial Intelligence (GeoAI), as the integration of geospatial studies and AI, has become one of the fastest-developing research directions in spatial data science and geography. This rapid change in the field calls for a deeper understanding of the recent developments and envision where the field is going in the near future. In this work, we provide a quantitative analysis of the GeoAI literature from the spatial, temporal, and semantic aspects. We briefly discuss the history of AI and GeoAI by highlighting some pioneering work. Then we discuss the current landscape of GeoAI by selecting five representative subdomains including remote …

Towards Resource-Efficient Reactive And Proactive Auto-Scaling For Microservice Architectures, Hussain Ahmad, Christoph Treude, Markus Wagner, Claudia Szabo

Research Collection School Of Computing and Information Systems

Microservice architectures have become increasingly popular in both academia and industry, providing enhanced agility, elasticity, and maintainability in software development and deployment. To simplify scaling operations in microservice architectures, container orchestration platforms such as Kubernetes feature Horizontal Pod Auto-scalers (HPAs) designed to adjust the resources of microservices to accommodate fluctuating workloads. However, existing HPAs are not suitable for resource-constrained environments, as they make scaling decisions based on the individual resource capacities of microservices, leading to service unavailability, resource mismanagement, and financial losses. Furthermore, the inherent delay in initializing and terminating microservice pods hinders HPAs from timely responding to workload fluctuations, …

Heartdj - Music Recommendation And Generation Through Biofeedback From Heart Rate Variability, Egemen Şahin

Dartmouth College Master’s Theses

This study investigates the integration of real-time physiological data with AI-generated music to enhance emotional well-being, stress regulation, and focus, using Heart Rate Variability (HRV) as a biomarker of autonomic function. Conducted in two phases—Stable Audio Open (SAO) and Suno (SUNO)—the research evaluates biofeedback-driven music interventions across varying daily music-listening habits.

In the SAO phase, short AI-generated instrumental tracks were compared with Spotify recommendations and guided meditation. Modest HRV improvements were observed in biofeedback conditions, but participants noted emotional limitations, citing short track lengths and abrupt transitions.

The SUNO phase addressed these limitations with longer, more complex AI-generated compositions combined …

A Robust Framework For Graph Construction In Vision Graph Neural Networks, Ismael Elsharkawi

Theses and Dissertations

In Computer Vision, the method of representing an image has a profound effect on the performance of a model. Traditionally speaking, an image is treated as a grid of pixels and can be processed via Convolution Neural Net- works (CNN). An image can also be treated as a sequence of patches. Vision Transformers and MLP-Mixers (Multi-Layer Perceptron Mixers) are two types of models that process an image as a sequence. A more generic representation than grids and sequences would be graphs. That is why Vision Graph Neural Network (ViG) construct a graph for an image and process the image as …

Deep Learning-Based Auto-Segmentation For Liver Yttrium-90 Selective Internal Radiation Therapy, Jun Li, Wookjin Choi, Rani Anne

Department of Radiation Oncology Faculty Papers

The aim was to evaluate a deep learning-based auto-segmentation method for liver delineation in Y-90 selective internal radiation therapy (SIRT). A deep learning (DL)-based liver segmentation model using the U-Net3D architecture was built. Auto-segmentation of the liver was tested in CT images of SIRT patients. DL auto-segmented liver contours were evaluated against physician manually-delineated contours. Dice similarity coefficient (DSC) and mean distance to agreement (MDA) were calculated. The DL-model-generated contours were compared with the contours generated using an Atlas-based method. Ratio of volume (RV, the ratio of DL-model auto-segmented liver volume to manually-delineated liver volume), and ratio of activity (RA, …

Playing The Digital Dialectic Game: Writing Pedagogy With Generative Ai, Rebekah Shultz Colby

University Writing Program: Faculty Scholarship

This article explores teaching writing with generative AI as critical play where students and teachers engage in an ethically dialectical and aleatory game with generative AI. I qualitatively surveyed 24 writing teachers about how they teach writing with generative AI as well as its advantages and disadvantages. I discovered that teachers used generative AI to teach about the ethics of generative AI's design and rhetorical use to avoid plagiarism. Teachers also critically played with generative AI to teach the writing process of invention, drafting, revision, and editing. Specifically, the critical, dialectical interplay of human and machine invents in aleatory and …

Unveiling The Potential Of Generative Artificial Intelligence: A Multidimensional Journey Into The Future, Keng Boon Ooi, Alex Koohang, Eugene Cheng Xi Aw, Tat Huei Cham, Cihan Cobanoglu, Charles Dennis, Yogesh K. Dwivedi, Jun Jie Hew, Heather Linton Kelly, Laurie Hughes, Chieh Yu Lin, Anubhav Mishra, Ian Phau, Ramakrishnan Raman, Marianna Sigala, Yun Chia Tang, Lai Wan Wong, Garry Wei Han Tan

Research outputs 2022 to 2026

Purpose: The launch of ChatGPT has brought the large language model (LLM)-based generative artificial intelligence (GAI) into the spotlight, triggering the interests of various stakeholders to seize the possible opportunities implicated by it. Nevertheless, there are also challenges that the stakeholders should observe when they are considering the potential of GAI. Given this backdrop, this study presents the viewpoints gathered from various subject experts on six identified areas. Design/methodology/approach: Through an expert-based approach, this paper gathers the viewpoints of various subject experts on the identified areas of tourism and hospitality, marketing, retailing, service operations, manufacturing and healthcare. Findings: The subject …

Incorporating Visual Information Into Natural Language Processing, Maxwell Mbabilla Aladago

Dartmouth College Ph.D Dissertations

Natural language describes entities in the world, some real and some abstract. It is also common practice to complement human learning of natural language with visual cues. This is evident in the heavily graphical nature of children’s literature which underscores the importance of visual cues in language acquisition. Similarly, the notion of “visual learners” is well recognized, reflecting the understanding that visual signals such as illustrations, gestures, and depictions effectively supplement language. In machine learning, two primary paradigms have emerged for training systems involving natural language. The first paradigm encompasses setups where pre-training and downstream tasks are exclusively in natural …

The Year Of Ai: Raising Campus Awareness Through Art, Exhibits, And Community Engagement, Essraa Nawar

Library Articles and Research

This poster highlights the Leatherby Libraries’ leadership in advancing AI literacy through creative, inclusive, and interdisciplinary approaches. As part of Chapman University’s “Year of AI,” the library launched initiatives such as Beyond the Lens and AI: The Next Chapter, blending art, ethics, and education to inspire campus-wide engagement. Through collaboration with IS&T, Town & Gown, and academic departments, the library positioned itself as a hub for ethical dialogue and innovation. The poster shares replicable models for how libraries can foster AI awareness through community partnerships, exhibitions, and experiential learning.

Sequential Convex Programming Using Safe Flight Corridor For Trajectory Planning Of Uavs, Zhu Wang, Zhenpeng Zhang, Mengtong Zhang, Guangtong Xu

Journal of System Simulation

Abstract: To address the issues of sensitivity to initial values and weak convergence of sequential convex programming(SCP) based time-optimal trajectory planning for UAVs, a SCP method using safety flight corridor, denoted as SFC-SCP(safe flight corridor-sequential convex programming) is proposed. According to the obstacle avoidance path obtained from the front-end path planning, a safe flight corridor is constructed by forming a convex polygon safe flight area without obstacles for each trajectory point. The non-convex obstacle avoidance constraint is converted into linear inequality constraints to improve convergence ability. The rear-end SCP method is used to transform the nonlinear trajectory optimization problem under …

Task Reallocation Method For Unmanned Swarm Under Adversarial Conditions, Lun Zhang, Mei Yang, Tuo Zhao, Shuiku Zhang, Jian Huang

Journal of System Simulation

Abstract: Heterogeneous unmanned swarms have important potential applications in future wars. However, during the high-intensity confrontation in the battlefield, how to efficiently and quickly redistribute the tasks carried by the damaged agents so that the swarms could successfully complete the mission is a difficult problem that must be addressed in the combat application of unmanned swarms. This paper proposes a task reallocation method named improved CNP-HA (contract net protocol-Hungarian algorithm). Through the allocation mechanism and the bidding mechanism, the method realizes the task reallocation of damaged agents with lower communication cost and faster speed comparing with baseline methods. In the …

Moving Target Velocity Measurement Method Based On Multi-View Observation Optimization Of Uav Image, Yuxin Wu, Zhilong Zhang, Aoxu Liu, Jiangwei Zou, Chuwei Li

Journal of System Simulation

Abstract: Measuring the position and velocity of moving targets is an important requirement for drone video analysis. In this paper, a moving target localization and velocity estimation algorithm based on least square optimization of UAV multi-view observation images is proposed: the video and corresponding pose parameters obtained by the airborne optoelectronic system are used to establish a line-of-sight model at multiple observation times, it is unified to the WGS-84 coordinate system by coordinate transformation, the position and velocity of the moving target are estimated based on the least squares algorithm. This algorithm does not require laser ranging information between the …