This paper introduces Graph World Models (GWMs) as a unified research paradigm, addressing the limitations of classical world models through structured graph representations. It proposes a novel taxonomy for GWMs based on relational inductive biases (spatial, physical, and logical) and discusses future research directions.

This paper introduces a formal logic of inability as a first-class concept, extending Coalition Logic to systematically study what multi-agent coalitions cannot achieve. It establishes the modal properties of this explicit inability operator, highlighting its significance for reasoning about constraints and safety in AI systems.

This paper investigates multimodal affect recognition in AI-assisted Computerized Cognitive Training (CCT), comparing appraisal dimensions and categorical labels across young and older adult populations. It demonstrates that appraisal dimensions consistently outperform and generalize better than categorical labels, especially across different age groups.

This paper introduces a Mixture of Experts (MOE)-powered semi-supervised inference framework that enhances Prediction-Powered Inference (PPI) by leveraging multiple predictors. The framework adapts to unknown predictor performance, combines their collective power, and offers a best-expert guarantee, improving inferential efficiency with abundant unlabeled data.

This article proposes a practical framework for engineering measurable trust in clinical AI systems, moving beyond subjective impressions of model performance. It emphasizes integrating evidence, human supervision, and staged autonomy within a multi-layered architecture to ensure safety and accountability in healthcare applications.