Digital Commons Network^™

Mvgamba : Unify 3d Content Generation As State Space Sequence Modeling, Xuanyu Yi, Zike Wu, Qiuhong Shen, Qingshan Xu, Pan Zhou, Joo-Hwee Lim, Shuicheng Yan, Xinchao Wang, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Recent 3D large reconstruction models (LRMs) can generate high-quality 3D content in sub-seconds by integrating multi-view diffusion models with scalable multi-view reconstructors. Current works further leverage 3D Gaussian Splatting as 3D representation for improved visual quality and rendering efficiency. However, we observe that existing Gaussian reconstruction models often suffer from multi-view inconsistency and blurred textures. We attribute this to the compromise of multi-view information propagation in favor of adopting powerful yet computationally intensive architectures (e.g., Transformers). To address this issue, we introduce MVGamba, a general and lightweight Gaussian reconstruction model featuring a multi-view Gaussian reconstructor based on the RNN-like State …

Lova3 : Learning To Visual Question Answering, Asking And Assessment, Henry Hengyuan Zhao, Pan Zhou, Difei Gao, Bai Shou, Mike Zheng Shou

Research Collection School Of Computing and Information Systems

Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. By enhancing these capabilities, humans can more effectively utilize data, leading to better comprehension and learning outcomes. Current Multimodal Large Language Models (MLLMs) primarily focus on question answering, often neglecting the full potential of questioning and assessment skills. Inspired by the human learning mechanism, we introduce LOVA3 , an innovative framework named “Learning tO Visual question Answering, Asking and Assessment,” designed to equip MLLMs with these additional capabilities. Our approach involves the creation of two supplementary training tasks GenQA and EvalQA, aiming …

Unified Generative And Discriminative Training For Multi-Modal Large Language Models, Wei Chow, Juncheng Li, Kaihang Pan, Qifan Yu, Hao Fei, Zhiqi Ge, Shuai Yang, Siliang Teng, Hanwang Zhang, Qianru Sun

Research Collection School Of Computing and Information Systems

In recent times, Vision-Language Models (VLMs) have been trained under two predominant paradigms. Generative training has enabled Multimodal Large Language Models (MLLMs) to tackle various complex tasks, yet issues such as hallucinations and weak object discrimination persist. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval, yet struggles with complex scenarios requiring fine-grained semantic differentiation. This paper addresses these challenges by proposing a unified approach that integrates the strengths of both paradigms. Considering interleaved image-text sequences as the general format of input samples, we introduce a structure-induced training strategy that imposes semantic relationships between input …

3d Snapshot: Invertible Embedding Of 3d Neural Representations In A Single Image, Yuqin Lu, Bailin Deng, Zhixuan Zhong, Tianle Zhang, Yuhui Quan, Hongmin Cai, Shengfeng He

Research Collection School Of Computing and Information Systems

3D neural rendering enables photo-realistic reconstruction of a specific scene by encoding discontinuous inputs into a neural representation. Despite the remarkable rendering results, the storage of network parameters is not transmission-friendly and not extendable to metaverse applications. In this paper, we propose an invertible neural rendering approach that enables generating an interactive 3D model from a single image (i.e., 3D Snapshot). Our idea is to distill a pre-trained neural rendering model (e.g., NeRF) into a visualizable image form that can then be easily inverted back to a neural network. To this end, we first present a neural image distillation method …

Mimicking To Dominate: Imitation Learning Strategies For Success In Multiagent Competitive Games, The Viet Bui, Tien Mai, Hong Thanh Nguyen

Research Collection School Of Computing and Information Systems

Training agents in multi-agent games presents significant challenges due to their intricate nature. These challenges are exacerbated by dynamics influenced not only by the environment but also by strategies of opponents. Existing methods often struggle with slow convergence and instability. To address these challenges, we harness the potential of imitation learning (IL) to comprehend and anticipate actions of the opponents, aiming to mitigate uncertainties with respect to the game dynamics. Our key contributions include: (i) a new multi-agent IL model for predicting next moves of the opponents --- our model works with hidden actions of opponents and local observations; (ii) …

Learning To Handle Complex Constraints For Vehicle Routing Problems, Jieyi Bi, Yining Ma, Jianan Zhou, Wen Song, Zhiguang Cao, Yaoxin Wu, Jie Zhang

Research Collection School Of Computing and Information Systems

Vehicle Routing Problems (VRPs) can model many real-world scenarios and often involve complex constraints. While recent neural methods excel in constructing solutions based on feasibility masking, they struggle with handling complex constraints, especially when obtaining the masking itself is NP-hard. In this paper, we propose a novel Proactive Infeasibility Prevention (PIP) framework to advance the capabilities of neural methods towards more complex VRPs. Our PIP integrates the Lagrangian multiplier as a basis to enhance constraint awareness and introduces preventative infeasibility masking to proactively steer the solution construction process. Moreover, we present PIP-D, which employs an auxiliary decoder and two adaptive …

Sprinql : Sub-Optimal Demonstrations Driven Offline Imitation Learning, Minh Huy Hoang, Tien Mai, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

We focus on offline imitation learning (IL), which aims to mimic an expert's behavior using demonstrations without any interaction with the environment. One of the main challenges in offline IL is the limited support of expert demonstrations, which typically cover only a small fraction of the state-action space. While it may not be feasible to obtain numerous expert demonstrations, it is often possible to gather a larger set of sub-optimal demonstrations. For example, in treatment optimization problems, there are varying levels of doctor treatments available for different chronic conditions. These range from treatment specialists and experienced general practitioners to less …

Self-Supervised Fine-Tuning For Neural Expert Finding, Budhitama Subagdja, Dan Sanchari, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Expert finding systems allow ones to find individuals who have expertise in specific fields or domains. Traditional expert finding are mostly based on topic modeling or keyword search methods that are limited in their capability to encode contextual knowledge from natural language. To address the limitation, this paper presents Neural Expert Finder (NEF), a novel method that takes a transfer learning approach based on transformer encoder networks to leverage the rich seman-tic and syntactic patterns of language encoded in pre-trained language models (PLMs). We propose a self-supervised learning approach utilizing contrastive training using both positive and automatically generated negative samples …

Improving Environment Novelty Quantification For Effective Unsupervised Environment Design, Jayden Teoh, Wenjun Li, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Unsupervised Environment Design (UED) formalizes the problem of autocurricula through interactive training between a teacher agent and a student agent. The teacher generates new training environments with high learning potential, curating an adaptive curriculum that strengthens the student’s ability to handle unseen scenarios. Existing UED methods mainly rely on regret, a metric that measures the difference between the agent’s optimal and actual performance, to guide curriculum design. Regret-driven methods generate curricula that progressively increase environment complexity for the student but overlook environment novelty–a critical element for enhancing an agent’s generalizability. Measuring environment novelty is especially challenging due to the underspecified …

Meta-Entrepreneurship: An Analysis Theory On Integrating Generative Ai, Agentic Ai, And Metaverse For Entrepreneurship, Yingying Zhang, Keng Siau

Research Collection School Of Computing and Information Systems

Metaverse entrepreneurship has emerged as an innovative topic alongside the development of generative AI, agentic AI and metaverse. This study conceptualizes meta-entrepreneurship as a novel form of entrepreneurial activity that enables value creation within virtual and physical realms and proposes an analytical theoretical framework based on a systematic literature review, observations, and focus group study. Our framework is structured around three layers (infrastructure, content, and experience) and two domains (metaverse-based operational domain and AI-based production domain), aims to conceptualize “what is meta-entrepreneurship” and identify new possibilities. The research highlights the multifaceted impact of meta-entrepreneurship on individuals, corporations, industries, societies, and …

Editorial For The Special Issue Of The Metaverse, Fiona Fui-Hoon Nah, Gert-Jan De Vreede, Lakshmi Goel, Eric Lim, Shu Schiller, Chee-Wee Tan

Research Collection School Of Computing and Information Systems

The metaverse is laying the groundwork for more accessible and immersive experiences by blending the physical and virtual worlds into a unified space where people can interact, create, and connect in entirely new ways. It holds the potential to revolutionize how we work, socialize, and learn, which in turn gives rise to unprecedented opportunities for innovation. In this special issue, we present four articles that depict the current state of research in metaverse, the key themes and theoretical underpinnings within this space, as well as emerging directions for future work. This special issue delivers valuable insights for both researchers and …

Virtual Conferencing Fatigue: Look‑Alike Avatar And Facial Attractiveness, Yuxin Liu, Keng Siau, Xueqing Wang, Yang Yang

Research Collection School Of Computing and Information Systems

The rapid evolution of avatar-related technologies provides extensive opportunities for diverse avatar applications in various areas. This study aims to investigate the innovative use of avatars to mitigate virtual conferencing fatigue, which refers to the physical and mental exhaustion from the inappropriate use of virtual conferencing applications. Grounded in Self-Awareness Theory, the research compares the impact of using real faces and user-look-alike avatars on virtual conferencing fatigue, delving into its underlying factors. In addition, the study examines the role of facial attractiveness enhancement on virtual conferencing fatigue. Laboratory experiments with a 2-by-2 between-subject design are employed to test hypotheses. The …

Exploring The Cognitive Sense Of Self In Ai: Ethical Frameworks And Technological Advances For Enhanced Decision-Making, Emily Barnes, James Hutson

Faculty Scholarship

The burgeoning field of Artificial Intelligence (AI) increasingly focuses on developing systems capable of self-awareness, merging technological innovation with deep ethical and philosophical considerations. This article explores the cognitive sense of self within AI, examining mechanisms through which AI systems may mirror human-like consciousness and self-perception. Despite significant advances, substantial gaps remain in the understanding and practical implementation of self-aware characteristics in AI, particularly in applying theoretical models and ethical frameworks to real-world scenarios. There is a pressing need for comprehensive research to explore these theoretical underpinnings and translate them into operational systems capable of ethical and adaptable behaviors. This …

Learning To Represent Temporal Dynamics And Generative Factors For Intelligent Visual Navigation, Sahand Khoshdel

All Theses

Visual navigation systems are crucial in various applications, including autonomous driving, unmanned aerial systems (UAS), and industrial automation. For these systems to operate efficiently in dynamic environments, they must not only interpret complex surroundings but also anticipate changes over time. Temporal prediction—forecasting environmental changes like moving obstacles or shifting lighting conditions—enables navigation systems to act proactively, enhancing both safety and performance. This dissertation investigates representation learning methods both as a backbone feature extractor for RL agents as well as a proxy for systems oriented for Explainable AI (XAI). Two main projects are presented as case studies to achieve the aforementioned …

Addressing Ethical Issues In Healthcare Artificial Intelligence Using A Lifecycle-Informed Process, Benjamin X Collins, Jean-Christophe Bélisle-Pipon, Barbara J Evans, Kadija Ferryman, Xiaoqian Jiang, Camille Nebeker, Laurie Novak, Kirk Roberts, Martin Were, Zhijun Yin, Vardit Ravitsky, Joseph Coco, Rachele Hendricks-Sturrup, Ishan Williams, Ellen W Clayton, Bradley A Malin, Bridge2ai Ethics And Trustworthy Ai Working Group

Faculty, Staff and Student Publications

OBJECTIVES: Artificial intelligence (AI) proceeds through an iterative and evaluative process of development, use, and refinement which may be characterized as a lifecycle. Within this context, stakeholders can vary in their interests and perceptions of the ethical issues associated with this rapidly evolving technology in ways that can fail to identify and avert adverse outcomes. Identifying issues throughout the AI lifecycle in a systematic manner can facilitate better-informed ethical deliberation.

MATERIALS AND METHODS: We analyzed existing lifecycles from within the current literature for ethical issues of AI in healthcare to identify themes, which we relied upon to create a lifecycle …

Efficient Anomaly Detection Driven By Different Machine Learning Architectures And Models, William Marfo

Open Access Theses & Dissertations

The rapid growth and ubiquitous adoption of the internet and cyber-physical systems (CPS) have fundamentally transformed modern communication, work, and human-system interactions. While networks now form the backbone of critical digital ecosystems, enabling seamless data transmission across diverse, interconnected systems, this increased connectivity also expands the attack surface, making real-time detection of network intrusions and anomalies a pressing challenge. Detecting unusual activities within network infrastructure requires advanced data traffic analysis to differentiate between legitimate and malicious interactions. Traditional approaches to network anomaly detectionâ??such as rule-based and signature-based systemsâ??often depend on predefined patterns to identify known anomalies, limiting their effectiveness against …

Neural Network Architecture Search Enabled Wide-Deep Learning (Nas-Wd) For Spatially Heterogenous Property Awared Chicken Woody Breast Classification And Hardness Regression, Chaitanya Pallerla, Yihong Feng, Casey M. Owens, Ramesh Bahadur Bist, Siavash Mahmoudi, Pouya Sohrabipour, Amirreza Davar, Dongyi Wang

Poultry Science Faculty Publications and Presentations

Due to intensive genetic selection for rapid growth rates and high broiler yields in recent years, the global poultry industry has faced a challenging problem in the form of woody breast (WB) conditions. This condition has caused significant economic losses as high as $200 million annually, and the root cause of WB has yet to be identified. Human palpation is the most common method of distinguishing a WB from others. However, this method is time-consuming and subjective. Hyperspectral imaging (HSI) combined with machine learning algorithms can evaluate the WB conditions of fillets in a non-invasive, objective, and high-throughput manner. In …

Time Series Decomposition Of Land Surface Temperature For Long-Term Trend Forecasting And Impact On Nesting Sea Turtle Habitats In The Arabian Gulf, Sachi Perera, Rommel H. Maneja, Mohamed Allali, Cyril Rakovski, Erik Linstead, Daniele Struppa, Ali Qasem, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

Improving land surface temperature (LST) modeling is vital for mitigating climate change effects on various ecosystems and marine habitats such as important sea turtle habitats. Over the past decade, extreme temperatures have likely significantly affected nesting sea turtle habitats in the Arabian Gulf, with predominantly female hatchlings creating an imbalance in the sex ratio. Such shifts have profound implications for these habitats’ long-term survival and conservation management. This study leverages statistical machine learning models to measure ongoing temporal variations in LST. We break down the LST time series into trend, seasonal, and noise components using classical decomposition methods like X11, …

Habit Coach: Customising Rag-Based Chatbots To Support Behavior Change, Arian Fooroogh Mand Arabi, Cansu Koyuturk, Michael O'Mahony, Raffaella Calati, Dimitri Ognibene

Conference papers

This paper presents the iterative development of Habit Coach, a GPT-based chatbot designed to support users in habit change through personalized interaction. Employing a user-centered design approach, we developed the chatbot using a Retrieval-Augmented Generation (RAG) system, which enables behavior personalization without retraining the underlying language model (GPT-4). The system leverages document retrieval and specialized prompts to tailor interactions, drawing from Cognitive Behavioral Therapy (CBT) and narrative therapy techniques. A key challenge in the development process was the difficulty of translating declarative knowledge into effective interaction behaviors. In the initial phase, the chatbot was provided with declarative knowledge about CBT …

A Systematic Review Of The Effects Of Ai-Assisted Moderation On Individuals And Groups, Zehui Yu, Lukas Otto, Dennis Assenmacher, Claudia Wagner

Human-Machine Communication

This review paper provides a conceptualization of AI-assisted content moderation with various degrees of autonomy and summarizes experimental evidence for how different levels of automation in content moderation and related losses of autonomy affect individuals and groups. Our results show that current research predominantly focuses on individuallevel effects, necessitating a shift toward understanding the impact on groups. The study highlights gaps in exploring different levels of AI-assisted moderation interventions and misalignments of different conceptualizations that make comparing research results difficult. The discussion underscores the prevailing emphasis on harmful content removal and advocates for investigating more constructive moderation techniques, emphasizing the …

Designing Customized Loss Functions For Training Deep Neural Networks, Ali Pourramezan Fard

Electronic Theses and Dissertations

This dissertation explores the critical role of loss functions in enhancing the predictive performance of deep machine learning models. Loss functions are an integral element of all the ongoing advances we witness daily in this domain. I design custom loss functions and their impacts on various machine learning tasks, particularly in computer vision.

In the first stage of my research, I aim to improve the prediction performance of deep learning models by providing them with more precise feedback associated with task requirements. This led me to create the concept of assistive loss functions. My first proposed loss function, inspired by …

An Overview Of Generative Ai Initiatives At Minnesota State University, Mankato (So Far), Evan Rusch, Nat Gustafson-Sundell

Library Services Publications

At Minnesota State University, Mankato, we’ve undertaken several experiments and initiatives focused on Generative Artificial Intelligence. We provided several examples at the Generative AI in Libraries (GAIL) conference. For this presentation, we provided a revised and expanded overview of our initiatives for the Northern Ohio Technical Services Librarians (NOTSL) Fall General Meeting. We explained license-related restrictions on uses of AI. We discussed the limitations of the retrieval-augmented generation tools currently available in the library. We summarized how we’ve tested ChatBots to support licensing and we showed how we’ve tried to use AI to improve data visualization for collections outreach. We …

Autonomous Driving Trajectory Prediction, Carlos Funes

Undergraduate Research Symposium Lightning Talks

Autonomous driving is undoubtedly one of the world's most revolutionary technologies, opening the door to a more secure traffic environment. This innovation has led to vehicles being able to drive by themselves without the necessity of a person behind the wheel, as well as cruise control, lane-keeping assist, and automatic emergency braking. Unfortunately, there is still plenty of work before autonomous driving becomes more popular among drivers. While at UNLV as an undergraduate student/research assistant, one of my goals is to learn how these technologies work to bring ideas into the automotive industry by refining solutions to problems within these …

It's Not As Bad As You Think: Detecting Ai-Generated Voices, Yong Qin Xu

Undergraduate Research Symposium Lightning Talks

Advances in machine learning have opened up the world to a brand new frontier of fraudulent phone calls which the average person may not be in any way prepared for. From imitations of a loved one's voice to lifelike mimicry of human callers, telephone scams may become harder than ever to anticipate or prevent now that criminals have the help of AI on their side. This is why in my research paper, I aim to analyze and compare two existing methods of detecting the authenticity of human voice recordings in order to demonstrate and explain currently available technology that's capable …

Vision-Language Integration For Enhanced Locomotion Mode Prediction, Ehsan Ahmadi

LSU Master's Theses

Wearable exoskeletons offer significant potential in enhancing human mobility in industrial environments. However, their adaptability to dynamic, task-intensive settings presents challenges, especially in accurately predicting locomotion modes such as ladder climbing, stair navigation, low-space movement, and obstacle navigation. This research proposes a multimodal framework that integrates visual data and speech commands to improve locomotion mode prediction in unpredictable environments. Multimodal data was collected using smart glasses, capturing both the user’s perspective (field-of-view, FOV) and voice during locomotion tasks. State-of-the-art models—CLIP, ImageBind, and GPT-4o—process these visual and linguistic inputs to predict locomotion activities. The models were evaluated in zero-shot and fine-tuned …

Ethical Risks And Challenges Of Chatgpt Applications In Education, Jingbo Fan, Hui Liang

Bulletin of Chinese Academy of Sciences (Chinese Version)

ChatGPT is a typical application in the field of natural language processing, with the potential to empower and revolutionize education. It can serve not only as a digital tutor for students but also as a virtual assistant for teachers, driving the transformation of student learning methods and teaching paradigms. Additionally, ChatGPT shows a wide range of applications in the research field. However, while bringing opportunities for educational development, ChatGPT also poses ethical risks and challenges to educational equity. Firstly, ChatGPT may exacerbate the digital divide, leading to unequal educational opportunities. Secondly, it presents risks such as knowledge alienation, algorithmic black-box …

Artificial Intelligence Foundation Model Risk Identification And Governance Model From Esg Perspective, Jincheng Shi, Guoyu Wang, Yingchun Wang

Bulletin of Chinese Academy of Sciences (Chinese Version)

The application ecology of artificial intelligence foundation model is rapidly expanding. The environment, society, and governance are facing new challenges and opportunities. Exploring the construction of a governance framework for the development risks of foundation model has important theoretical value and practical significance for promoting the healthy and sustainable development of artificial intelligence. Based on the theories of ESG and artificial intelligence governance, this study analyzes the development benefits and typical risks of foundation model from the perspective of ESG and then constructs a risk governance framework and implementation strategies for artificial intelligence foundation models. This study shows that a …

Participatory Ethical Regulations: Risk Challenges Of Artificial Intelligence Era And Construction Of Governance Logic, Chenggang Zhang, Lu Pan

Bulletin of Chinese Academy of Sciences (Chinese Version)

Participatory ethical norms emphasize the involvement of diverse stakeholders, aiming to construct a more comprehensive and balanced ethical governance framework. The rapid development of artificial intelligence (AI) technology is leading society through unprecedented transformations, significantly impacting ethical perspectives, social governance models, and the symbiotic relationship between humans and technology. The participatory ethical norms, characterized by multi-stakeholder participation, interactivity, and openness, represent a crucial pathway for addressing the challenges posed by the rapid development of AI technology. Constructing an AI governance framework based on participatory ethical norms provides solutions for the sustainable, fair, and transparent development of AI from multiple aspects …

Overview On Autonomous Machine Computing, Shaoshan Liu, Yiming Gan, Yinhe Han

Bulletin of Chinese Academy of Sciences (Chinese Version)

Autonomous machine computing, an innovative blend of algorithms, software, and cutting-edge computing hardware, is poised to be the next major paradigm shift in the global economy, following personal, mobile, and cloud computing. This study delves into the research and commercialization of the robotics industry, underscoring the critical importance of establishing a comprehensive autonomous machine computing ecosystem. This study argues that autonomous machine computing necessitates a complete ecosystem that encompasses applications, programming languages, and the foundational hardware architectures, and presents a comprehensive review of significant research contributions across these areas. Moreover, the study explores the synergy between autonomous machine computing and …

Enlightenment Of Us Nairr To Construction Of Artificial Intelligence Innovation Ecosystem In China, Tian Jiang, Li Qian

Bulletin of Chinese Academy of Sciences (Chinese Version)

The National Artificial Intelligence Research Resource (NAIRR) of the United States is of great significance for addressing the new challenges faced by the innovation of artificial intelligence technology. For China, the experience of NAIRR provides valuable references in resource optimization allocation and efficient utilization, which helps us to overcome resource bottlenecks and promote the rapid development of artificial intelligence technology. This study analyzes the enlightenment of NAIRR to the innovation and development of artificial intelligence in China from two key aspects. The first is the innovation-driven elements, where the integration strategies of NAIRR in computing and storage power, data resource, …