Artificial Intelligence and Robotics Commons^™

Deconstructing The Black Box: An Explainability Analysis Of Deep Learning Architectures In Cytopathology, Chase A. Garrett

SACAD: Scholarly Activities

Deep learning shows strong potential in medical-image analysis, yet adoption in cyptopathology

remains limited. Cytopathology could benefit from deep learning applications by improving

diagnostic efficiency and accuracy. However deep learning comes with a notorious “black box”

that keeps the models from being transparent and trustworthy for widespread clinical adoption.

We conducted a comprehensive and comparative analysis of several deep learning architectures

for multi-class classification of acute leukemia types, ALL, AML, and normal healthy cells from

peripheral blood smear images. The models in this research include a Vision Transformer (ViT)

and a diverse selection of Convolutional Neural Network (CNN) models. The …

Pre-Experiential Constraint Reconstruction: A Structural Account Of The Prior Layer In Dialogue With Jung, Griselda Poe

Publications and Research

Experiences commonly described as pre-experiential memory—such as immediate recognition, familiarity without prior exposure, and the sense of "already knowing"—are typically interpreted as the retrieval of stored content. However, this storage-based account does not provide a structurally consistent explanation of how such content is preserved prior to experience or reactivated in a form that aligns with present input.

This paper extends the three-layer cognitive architecture developed in prior work in this series (Poe, 2026n), in which cognition operates across Core processing, Modulation, and an operationally inaccessible Prior layer that supplies constraints to all processing.

This paper proposes an alternative account in …

Dual History Enhancement With Hybrid Hypergraph-Graph Networks For Temporal Knowledge Graph Reasoning, Kailun Ye, Xiangjie Kong, Yuchao Zhang, Xuan Wang, Linan Zhu, Jiaxin Du, Guojiang Shen, Jianxin Li

Research outputs 2022 to 2026

Temporal Knowledge Graph (TKG) reasoning seeks to predict future events by analyzing historical data, where the effective leverage of both local and global historical facts proves crucial. Existing approaches employ graph neural networks (GNNs) and recurrent neural networks (RNNs) for local evolution patterns, complemented by statistical methods to enhance attention to global facts, demonstrating efficient predictive capabilities. However, traditional GNNs, constrained by their low-order neighborhood aggregation design, inherently fail to model potential high-order dependencies among facts. Furthermore, existing global history modeling approaches may introduce irrelevant historical information that interferes with prediction tasks. To address these limitations, we propose a Dual …

Does Culture Translate? A Case Study On Artificial Intelligencegenerated Text Concerning Japanese-Style Employment, Kanji Kitamura

Languages, Literatures, and Cultures Faculty Publications

Translation matters to international business when it has a discernible impact on firm performance or critical business processes. Current developments include machine translation, which is evolving in tandem with generative artificial intelligence (AI). On one hand, useful translation apps have become available to help the public communicate internationally. On the other hand, recent research concludes that even machine translation's best output still requires post-editing by a human. This argument implies that a machine-translated, grammatically accurate text may not always make sense to a human audience, possibly because of a semantic-pragmatic issue beyond the lexical level. This paper regards it as …

Statistical Inference Is Not Moral Reasoning: The Case Against Ai On Hospital Ethics Boards, Elan J. Haronian

Seaver College Research And Scholarly Achievement Symposium

As generative AI becomes more integrated in healthcare, it seems inevitable that AI will eventually be used on hospital ethics committees. However, before implementation, their roles need careful consideration. Although AI promises to reduce costs, increase efficiency, and reduce human workloads, there are important ways in which it is limited, especially when human emotion and connection are crucial, as in clinical ethics boards.

In this paper, I highlight several problems preventing AI from being useful on hospital ethics boards. These include issues of opaque reasoning (the “black box” problem), liability, transparency, privacy, and consent. While there are proposed frameworks for …

Older Adults And Emerging Technology Fraud In The Ai Deepfake Era, Thiago Neves

Research Days

Artificial intelligence has accelerated faster than society's ability to adapt, leaving older adults extremely vulnerable to AI-generated fraud. Americans over age 60 lost $4.9 billion to scams in 2024, 43% more than the previous year. In this research, I investigate how digital illiteracy, combined with AI-generated deepfakes, creates this crisis. Older adults struggle with three principal vulnerabilities: distinguishing legitimate sites from scams, judging whether online information is truthful, and understanding how algorithms use their data. AI weaponizes these gaps through voice clones, synthetic video calls, and personalized phishing emails that avoid the trust cues seniors tend to rely on. I …

The Core-Modulation Architecture (Cma): A Structural Overview Of Hallucination As Structural Mismatch, Griselda Poe

Publications and Research

Hallucination is defined not as factual error but as a structural failure of alignment across target, layer, and constraint.

Within the Core-Modulation Architecture (CMA), cognition proceeds through layered processing and requires layer-specific termination conditions. Hallucination arises when Modulation-level termination is registered as completion while Core-level resolution has not occurred, producing structurally ungrounded but locally coherent outputs.

Detection is therefore structural rather than content-based, focusing on layer mismatch and termination failure.

This document presents a minimal structural account of hallucination within the CMA framework.

Advice For Incorporating Ai Tools Into Your Legal Practice, Celia Bigoness, Robert A. Mackenzie, David J. Reiss

Cornell Law Faculty Publications

We have been speaking with many lawyers and law students about using generative artificial intelligence (AI) tools in their legal practice. We are struck by the fact that many of them have not been experimenting much, if at all, with the tools that are available to them - although many acknowledge that their clients are increasingly integrating generative AI into their businesses. We have been integrating a lot of these tools into our own professional lives, and here are some tips to help lawyers and law students get comfortable with AI tools that can help them, in big ways and …

Motivation Without Borders: Applying The Octalysis Framework To Global Faculty And Student Engagement In Ai Era, Harika Rao

Faculty and Staff Publications & Presentations

No abstract provided.

A Comprehensive Survey Of Agentic Ai: Design Principles, Security Risks, And Ethical Consideration, Md Shaba Sayeed

ATU Scholars Symposium

In the past several years, the world has managed to transition away from simple automation to independent AI systems. Agentic AI is an agent that can work independently, carrying out all essential plans and implementations without any kind of supervision from a human being. This review has tried to demonstrate the transformative impact that Agentic AI brings to contemporary models of intelligence by means of synthesis of perception, reasoning, and goal. We utilized the phrases Agentic AI, autonomous AI, multi agent systems as keywords in Google Scholar, ScienceDirect, arXiv, and other digital libraries. We have used these 38 main papers …

Dermal: A Multi-Input Deep Learning Model For Improving Access To Dermatological Screening, Aubreye Freeman

ATU Scholars Symposium

According to the World Health Organization's press release on December 12, 2024, global healthcare spending is dropping significantly, leaving a large percentage of the world without proper healthcare. In an attempt to alleviate this problem, with respect to the field of dermatology, we created a deep learning model, Dermatology Enhanced by Recognition and Machine Aided Learning (DERMAL), to assist in diagnosing skin conditions. DERMAL was trained on a portion of the Google and Stanford Medicine's SCIN dataset, which has more than 10,000 images of various skin conditions. The 9 most common skin conditions of the dataset were selected as the …

Llm-Based Stock Sentiment And Market Intelligence Platform, Joshua Thrower, Andrew Pinkerton, Ian Duggan, Wyatt Lester

ATU Scholars Symposium

Financial markets increasingly react to social media discourse, yet investors lack tools to translate this unstructured commentary into measurable indicators. Platforms such as YouTube host extensive discussions about publicly traded equities, but extracting reliable sentiment trends from high-volume, noisy comment streams remains technically challenging. This project develops a stock sentiment and market intelligence platform that transforms YouTube comment data into aggregated sentiment indicators aligned to specific equities. Comments are mapped to equities using ticker specific keyword identification combined with contextual filtering to reduce false associations from ambiguous or off-topic mentions. The system assigns numerical sentiment scores to individual comments and …

Ai Exposure And The Future Of Work: Tasks, Skill Demand, And Education, Erik Vasilauskas, Michael Horrigan

External Papers and Reports

No abstract provided.

Ai Method For Classification Of Diagnosis Of Near-Infrared Breast Lesion Images, Kaiquan Chen, Fangyang Shen, Honggang Wang, Zhengchao Dong, Jizhong Xiao, Ming Ma, Afroza Aktar, Christopher Chow, Wenxiong Zhang

Publications and Research

In near-infrared optical breast lesion screening and diagnosis systems, high-speed four-dimensional scanners can dynamically acquire tens of thousands of lesion images within a five-minute period. Currently, manual computer annotation is required to generate standard samples from these scanned breast lesion images, a process that depends heavily on physicians with clinical expertise. On average, a single physician can annotate only approximately ten samples per working day. As a result, this process is time-consuming and labor-intensive, and the collected samples often suffer from low accuracy, large variability, and limited diagnostic reliability. Several AI-based annotation tools, such as QuPath, HALO AI™, and X-AnyLabeling, …

Towards Physics-Informed Neural Networks For Simulating Multiphase Geothermal Convection​*, Daniel C. Patton, Andrew Harrison Eno

Campus Research Month

Water and steam flow through porous rock, transferring heat via conduction and buoyancy-driven convection caused by density differences. Traditional numerical methods (finite-volume/finite-element) model this well but can become memory-intensive and unstable for long, high-detail simulations. This work demonstrates a Physics-Informed Neural Network (PINN) using a finite-difference approach within the NVIDIA PhysicsNeMo framework to simulate magma chambers in 2D. Tested on the Rio Pisco pluton in Peru, results are compared with the USGS HYDROTHERM model. PINNs learn from physical laws, offering accurate, flexible solutions with less data and development effort.

Towards Smaller Artificial Neural Network Using Mean Compression*, Michael D. Burks, Matthew K. Chuhng

Campus Research Month

Artificial Neural Networks (ANNs) require substantial memory and computational resources, limiting their deployment on resource-constrained devices. Our contribution is a compression method using Mean Compression (MC) to reduce ANN size while preserving functionality and accuracy. MC consolidates connections with similar edge weights into meta-nodes with averaged values. Unlike traditional pruning that only removes connections among neurons, MC restructures networks by recomputing weights and creating meta-nodes. Additionally, unlike fixed pruning thresholds, MC uses flexible weight range patterns. Applied to multilayer perceptron (MLP), ANNs are made more accessible for deployment on constrained devices as proven in several experiments. Specifically, across five classification …

Threat-Analysis Oriented Digital Twinning Of Ml-Powered Future Autonomous Weapon Systems, Thomas Neubert

Doctoral Dissertations and Master's Theses

Warfare is undergoing a rapid transformation with the integration of artificial intelligence (AI) and machine learning (ML) into autonomous weapon systems (AWS) for perception, decision support, and control. As these systems become more software-defined, their cyber attack surface expands across sensing, communications, autonomy logic, and human-machine interfaces. As human oversight diminishes, ensuring the cybersecurity, resilience, and reliability of these systems becomes critical to mission success. This thesis investigates how a digital twin-driven threat modeling framework that integrates system-centric analysis with adversary-informed methodologies can support structured cybersecurity vulnerability evaluation and defensive strategy development associated with ML-powered AWS. First, the study analyzes …

The Expanding Digital Border: Ai, Surveillance, And The Fight For Justice, James Chesser

Immigration and Human Rights Law Review

As artificial intelligence transforms the mechanisms of immigration control, the modern border has become a digital filter—one governed less by geography and more by code. This Article examines the legal, technical, and ethical implications of AI-driven systems now central to global border enforcement, including biometric surveillance, algorithmic risk scoring, and predictive profiling. It explores how states use these technologies not only to manage irregular migration, but to compete for global talent—constructing migration regimes that reward capital and compliance while eroding transparency, due process, and equality.

Through an international and comparative lens, the piece highlights the expansion of algorithmic decision-making across …

Ai Models As Cultural Beings: Investigating Ai Cultural Biases And The Impact Of Cultural Alignment On Human-Ai Creative Collaboration, Choon Ngee Tan, Meng Han, Roy Y. J. Chua, Chi-Ying Cheng

Research Collection Lee Kong Chian School Of Business

Existing research on AI cultural biases predominantly focuses on Western models, overlooking critical gaps in non-Western models. We conduct a comparative analysis of AI models – ChatGPT (U.S. developed) and ErnieBot (China developed) – from different cultures to investigate how corresponding cultural biases manifest in their outputs. Additionally, we examine how cultural alignment between human users and AI models impacts their collaborative creative performance and the underlying psychological mechanisms. In Study 1, multi-choice prompt with zero-shot technique was used to evaluate cultural biases in four widely used AI models – ChatGPT-3.5/4, ErnieBot-3.5/4 – comparing their responses to established cultural psychometric …

Autologger: A Multi-Agent Framework For The End-To-End Automated Logging, Renyi Zhong, Yintong Huo, Wenwei Gu, Yichen Li, Michael R. Lyu

Research Collection School Of Computing and Information Systems

Software logging is critical for system observability, yet developers face a dual crisis of costly overlogging and risky underlogging. Existing automated logging tools often overlook the fundamental whether-to-log decision and struggle with the composite nature of logging. In this paper, we propose AutoLogger, a novel hybrid framework that addresses the complete the end-to-end logging pipeline. AutoLogger first employs a fine-tuned classifier, the Judger, to accurately determine if a method requires new logging statements. If logging is needed, a multi-agent system is activated. The system includes specialized agents: a Locator dedicated to determining where to log, and a Generator focused on …