Related papers: Token Space: A Category Theory Framework for AI Co…
AGI has become the Holly Grail of AI with the promise of level intelligence and the major Tech companies around the world are investing unprecedented amounts of resources in its pursuit. Yet, there does not exist a single formal definition…
Discrete diffusion language models have emerged as a competitive alternative to auto-regressive language models, but training them efficiently under limited parameter and memory budgets remains challenging. Modern architectures are…
This paper presents a transformative framework for artificial neural networks over graded vector spaces, tailored to model hierarchical and structured data in fields like algebraic geometry and physics. By exploiting the algebraic…
Recent advances in artificial intelligence research have led to a profusion of studies that apply deep learning to problems in image analysis and natural language processing among others. Additionally, the availability of open-source…
Token representations influence the efficiency and adaptability of language models, yet conventional tokenization strategies impose rigid segmentation boundaries that do not adjust dynamically to evolving contextual relationships. The…
Transformers are widely used in computer vision areas and have achieved remarkable success. Most state-of-the-art approaches split images into regular grids and represent each grid region with a vision token. However, fixed token…
In recent years, the integration of artificial intelligence (AI) and cloud computing has emerged as a promising avenue for addressing the growing computational demands of AI applications. This paper presents a comprehensive study of…
Modern digital applications extensively integrate Artificial Intelligence models into their core systems, offering significant advantages for automated decision-making. However, these AI-based systems encounter reliability and safety…
A generative design based on topology optimization provides diverse alternatives as entities in a computational model with a high design degree. However, as the diversity of the generated alternatives increases, the cognitive burden on…
Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…
In this report we present a new modelling framework for concepts based on quantum theory, and demonstrate how the conceptual representations can be learned automatically from data. A contribution of the work is a thorough category-theoretic…
Argument Unit Recognition and Classification aims at identifying argument units from text and classifying them as pro or against. One of the design choices that need to be made when developing systems for this task is what the unit of…
Neural network-based clustering has recently gained popularity, and in particular a constrained clustering formulation has been proposed to perform transfer learning and image category discovery using deep learning. The core idea is to…
Explainability is a longstanding challenge in deep learning, especially in high-stakes domains like healthcare. Common explainability methods highlight image regions that drive an AI model's decision. Humans, however, heavily rely on…
In this paper, we present methods for two types of metacognitive tasks in an AI system: rapidly expanding a neural classification model to accommodate a new category of object, and recognizing when a novel object type is observed instead of…
We give a brief account of a construction called tokens here, which is significant in algebra, analysis, combinatorics, and physics. Tokens allow to express a semigroup on one set via a semigroup convolution on another set. Therefore tokens…
Large language models (LLMs) demonstrate strong capabilities in in-context learning, but verifying the correctness of their generated responses remains a challenge. Prior work has explored attribution at the sentence level, but these…
To improve the trustworthiness of an AI model, finding consistent, understandable representations of its inference process is essential. This understanding is particularly important in high-stakes operations such as weather forecasting,…
Racial diversity has become increasingly discussed within the AI and algorithmic fairness literature, yet little attention is focused on justifying the choices of racial categories and understanding how people are racialized into these…
Written to be contributed as the "mathematical modeling" chapter of a book, edited by Elaine Landry, to be titled "Categories for the Working Philosopher". In this chapter, category theory is presented as a mathematical modeling framework…