Skip to content

Category

graph neural networks

1,828 papers

#artificial intelligence Open access Aug 2026

Does ChatGPT Undermine Human Epistemic Authority? A Multi-Dimensional Analysis of Artificial Intelligence's Challenge to Knowledge Systems

The emergence of ChatGPT and similar large language models has precipitated fundamental questions about the nature and distribution of epistemic authority in contemporary knowledge systems. This comprehensive analysis examines whether ChatGPT undermines human epistemic authority through a multi-dimensional theoretical...

Kwan Hong TAN · 0 citations
#artificial intelligence Open access Jul 2026

Beyond Participatory Explanation: Ontological Reflexivity Theory as a Resolution to the Consciousness Emergence Problem

David Cota’s evaluation of the author’s “participatory explanation” approach to consciousness reveals fundamental conceptual problems that plague contemporary consciousness studies. Cota identifies a critical conflation between reason as a symbolic-operational function, and consciousness as a phenomenal-experiential fi...

Kwan Hong TAN · 0 citations
#artificial intelligence Open access Jul 2026

Beyond Participatory Explanation: Ontological Reflexivity Theory as a Resolution to the Consciousness Emergence Problem

David Cota’s evaluation of the author’s “participatory explanation” approach to consciousness reveals fundamental conceptual problems that plague contemporary consciousness studies. Cota identifies a critical conflation between reason as a symbolic-operational function, and consciousness as a phenomenal-experiential fi...

Kwan Hong TAN · 0 citations
#artificial intelligence Open access Aug 2026

The Autonomy Externality: A Welfare-Economic Model of Agentic Artificial Intelligence, Correlated Failure, and Optimal Assurance Policy

Agentic artificial intelligence is shifting automation from prediction and recommendation toward autonomous execution. This transition creates an economic externality that is not captured by conventional firm-level investment models. A firm receives much of the productivity benefit from delegating decisions to an artif...

Kwan Hong TAN · 1 citation
#graph neural networks Open access Sep 2026

DeepLog

Added One module for N formulas. DeepLogModuleFactory.compile(*nodes) takes any number of formula ASTs and returns one module with a column per formula, in the order given. Before, N formulas meant N compile calls — N circuit factories, N knowledge compilations, and a copy of every predicate module per formula — even w...

Robin Manhaeve, Stefano Colamonaco, Vincent Derkinderen et al. · 0 citations
#graph neural networks Dataset Open access Sep 2026

Jincheng Zhang’s Collection of 44,123 Original Sole-Authored Computer Science Preprints, Released on September 28, 2026

On September 28, 2026, Jincheng Zhang released a large-scale collection of 44,123 original computer science preprints. All 44,123 papers are sole-authored research works written by Jincheng Zhang himself. The collection is not a bibliography, compilation, or repository of papers authored by other researchers; rather, i...

Jincheng Zhang · 0 citations
#graph neural networks Open access Sep 2026

AI-Enabled Land-Use–Transport Decision Support for Bike-Sharing Expansion: Reproducibility Package

Code, Colab notebooks, configurations, trained checkpoints and derived results for the article "AI-Enabled Land-Use–Transport Decision Support for Bike-Sharing Expansion: Spatial Transfer, Station-Mediated Accessibility, and Policy Frontiers" (under review in Transportation Research Part A: Policy and Practice, special...

Igor Betkier · 0 citations
#graph neural networks Open access Sep 2026

Longitudinal Artificial Intelligence for Parkinson’s Disease: Modern Modelling, Feature Selection, and Imputation – A Technical Review and Clinical Roadmap

Parkinson’s disease (PD) research has been reshaped by large-scale multi-modal longitudinal datasets and advances in artificial intelligence (AI) and machine learning (ML). This review synthesises the current state of longitudinal modelling, feature selection, and missing-data imputation for PD, drawing on 154 studies...

Moad Hani, Nacim Betrouni, Saïd Mahmoudi et al. · 0 citations
#graph neural networks Open access Sep 2026

Béton Roman Augmenté et Architecture Décentralisée

Résumé FRCe document, produit avec l’assistance de Gemini 3 Raisonnement, est publié sous licence Apache 2.0. Il constitue une publication défensive volontaire (antériorité) et entre de ce fait dans l’état de la technique au sens des législations applicables : art. 54(2) CBE (Convention sur le brevet européen), art. L...

Xavier Pillet · 0 citations
#graph neural networks Open access Sep 2026

AI-Powered Emotion Detection from EEG Signals

Emotion recognition from brain activity has emerged as an important research area in affective computing, with electroencephalography (EEG) providing a direct physiological signal for identifying emotional states. This study presents a controlled experimental comparison of three deep learning architectures—one-dimensio...

Naveen Saini · 0 citations
#graph neural networks Open access Sep 2026

Longitudinal Artificial Intelligence for Parkinson’s Disease: Modern Modelling, Feature Selection, and Imputation – A Technical Review and Clinical Roadmap

Parkinson’s disease (PD) research has been reshaped by large-scale multi-modal longitudinal datasets and advances in artificial intelligence (AI) and machine learning (ML). This review synthesises the current state of longitudinal modelling, feature selection, and missing-data imputation for PD, drawing on 154 studies...

Moad Hani, Nacim Betrouni, Saïd Mahmoudi et al. · 0 citations
#graph neural networks Open access Sep 2026

AI-Driven Logic Synthesis and Optimization in Modern Electronic Design Automation: From Learned Heuristics to Generative Circuit Design

AbstractThe exponential growth in integrated circuit (IC) complexity, combined with tight power, performance and area (PPA) limits, has strained traditional Electronic Design Automation (EDA) techniques. Classical logic synthesis relies on hand-engineered heuristics whose runtime and solution quality struggle to scale...

Rainean Fordelon · 0 citations

From tech blogs

See all →
Microsoft Research Blog Jul 13, 2026

Verifying Rust cryptography in SymCrypt, from standards to code

Cryptographic code supports vital protections in modern computing systems. Learn how a new method helps verify code as developers write it while preserving speed and adaptability as it gets implemented and evolves. The post Verifying Rust cryptography in SymCrypt, from standards to code appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.