Cognitive Science and Education Research

Últimos artículos

• Soft Symbol Grounding for Prototypical Concepts

  Marcos Galv\'an-L\'opez, Nijesh Upreti, Hiram Calvo, Carlos Aguilar-Ib\'a\~nez, Vaishak Belle · 14 de septiembre de 2026

  Neuro-symbolic models are usually trained with supervision only on final labels, leaving the intermediate concepts unobserved. Since many concept assignments are consistent with a given label, training can predict labels correctly while recovering the wrong concepts, a failure known as a reasoning s…

• A First-Principles Theory of Slow Thinking and Active Perception

  Hongkang Yang, Zhi-Qin John Xu, Feiyu Xiong, Weinan E · 10 de julio de 2026

  As part of a series on first-principles modeling of cognitive functions, this paper attempts to provide a mathematical formulation of thinking and perception. It formally derives slow thinking or more generally, active perception, and encompasses the design, training and inference of slow thinking l…

• CoT-Space: A Theoretical Framework for Internal Slow-Thinking via Reinforcement Learning

  Zeyu Gan, Hao Yi, Yong Liu · 5 de junio de 2026

  Test-time scaling, primarily manifested through multi-step Chain-of-Thought (CoT) reasoning via Reinforcement Learning (RL), has emerged as a pivotal paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). However, a significant theoretical gap persists: traditional token-…

• Soft-TransFormers for Continual Learning

  Haeyong Kang, Chang D. Yoo · 29 de abril de 2026

  Inspired by the \emph{Well-initialized Lottery Ticket Hypothesis (WLTH)}, we introduce Soft-Transformer (Soft-TF), a parameter-efficient framework for continual learning that leverages soft, real-valued subnetworks over a frozen pre-trained Transformer. Instead of relying on manually designed prompt…

• Information-Theoretic Measures in AI: A Practical Decision Guide

  Nikolaos Al. Papadopoulos, Konstantinos E. Psannis · 28 de abril de 2026

  Information-theoretic (IT) measures are ubiquitous in artificial intelligence: entropy drives decision-tree splits and uncertainty quantification, cross-entropy is the default classification loss, mutual information underpins representation learning and feature selection, and transfer entropy reveal…

• The Non-Optimality of Scientific Knowledge: Path Dependence, Lock-In, and The Local Minimum Trap

  Mohamed Mabrok · 15 de abril de 2026

  Science is widely regarded as humanity's most reliable method for uncovering truths about the natural world. Yet the \emph{trajectory} of scientific discovery is rarely examined as an optimization problem in its own right. This paper argues that the body of scientific knowledge, at any given histori…

• A Mathematical Theory of Understanding

  Bahar Ta\c{s}kesen · 23 de marzo de 2026

  Generative AI has transformed the economics of information production, making explanations, proofs, examples, and analyses available at very low cost. Yet the value of information still depends on whether downstream users can absorb and act on it. A signal conveys meaning only to a learner with the …

• Proceedings of the 2nd Workshop on Advancing Artificial Intelligence through Theory of Mind

  Nitay Alon, Joseph M. Barnby, Reuth Mirsky, Stefan Sarkadi · 20 de marzo de 2026

  This volume includes a selection of papers presented at the 2nd Workshop on Advancing Artificial Intelligence through Theory of Mind held at AAAI 2026 in Singapore on 26th January 2026. The purpose of this volume is to provide an open access and curated anthology for the ToM and AI research communit…

• One-Step Flow Q-Learning: Addressing the Diffusion Policy Bottleneck in Offline Reinforcement Learning

  Thanh Nguyen, Chang D. Yoo · 25 de febrero de 2026

  Diffusion Q-Learning (DQL) has established diffusion policies as a high-performing paradigm for offline reinforcement learning, but its reliance on multi-step denoising for action generation renders both training and inference slow and fragile. Existing efforts to accelerate DQL toward one-step deno…

• Epistemology of Generative AI: The Geometry of Knowing

  Ilya Levin · 20 de febrero de 2026

  Generative AI presents an unprecedented challenge to our understanding of knowledge and its production. Unlike previous technological transformations, where engineering understanding preceded or accompanied deployment, generative AI operates through mechanisms whose epistemic character remains obscu…

• A Foundational Theory for Decentralized Sensory Learning

  Linus M{\aa}rtensson, Jonas M. D. Enander, Udaya B. Rongala, Henrik J\"orntell · 18 de febrero de 2026

  In both neuroscience and artificial intelligence, popular functional frameworks and neural network formulations operate by making use of extrinsic error measurements and global learning algorithms. Through a set of conjectures based on evolutionary insights on the origin of cellular adaptive mechani…

• GRAPHMOE: Amplifying Cognitive Depth of Mixture-of-Experts Network via Introducing Self-Rethinking Mechanism

  Bo Lv, Chen Tang, Zifan Zheng, Bohao Yang, Kun Zhao, Ning Liao, Xiaoxing Wang, Feiyu Xiong, Zhiyu Li, Nayu Liu, Jingchi Jiang · 24 de diciembre de 2025

  Traditional Mixture-of-Experts (MoE) networks benefit from utilizing multiple smaller expert models as opposed to a single large network. However, these experts typically operate independently, leaving a question open about whether interconnecting these models could enhance the performance of MoE ne…

• Mathematics of natural intelligence

  Evgenii Vityaev · 15 de diciembre de 2025

  In the process of evolution, the brain has achieved such perfection that artificial intelligence systems do not have and which needs its own mathematics. The concept of cognitome, introduced by the academician K.V. Anokhin, as the cognitive structure of the mind -- a high-order structure of the brai…

• Marti-5: A Mathematical Model of "Self in the World" as a First Step Toward Self-Awareness

  Igor Pivovarov, Sergey Shumsky · 15 de diciembre de 2025

  The existence of 'what' and 'where' pathways of information processing in the brain was proposed almost 30 years ago, but there is still a lack of a clear mathematical model that could show how these pathways work together. We propose a biologically inspired mathematical model that uses this idea to…

• Object-centric proto-symbolic behavioural reasoning from pixels

  Ruben van Bergen, Justus H\"ubotter, Alma Lago, Pablo Lanillos · 12 de diciembre de 2025

  Autonomous intelligent agents must bridge computational challenges at disparate levels of abstraction, from the low-level spaces of sensory input and motor commands to the high-level domain of abstract reasoning and planning. A key question in designing such agents is how best to instantiate the rep…

• Inclusive education via empathy propagation in schools of students with special education needs

  Igor Lugo, Martha G. Alatriste-Contreras, Brenda G. Couti\~no-V\'azquez · 21 de noviembre de 2025

  This study presents a theoretical model for identifying emergent scenarios of inclusiveness related to student with special education needs (SEN). Based on variations of the Shelling model of segregation, we explored the propagation of thinking about others as equals (empathy) in students with and w…

• Duality-based Mode Operations and Pyramid Multilayer Mapping for Rhetorical Modes

  Zi-Niu Wu · 11 de noviembre de 2025

  Rhetorical modes are useful in both academic and non-academic writing, and can be subjects to be studied within linguistic research and computational modeling. Establishing a conceptual bridge among these domains could enable each to benefit from the others. This paper proposes duality-based mode op…

• The Kinetics of Reasoning: How Chain-of-Thought Shapes Learning in Transformers?

  Zihan Pengmei, Costas Mavromatis, Zhengyuan Shen, Yunyi Zhang, Vassilis N. Ioannidis, Huzefa Rangwala · 31 de octubre de 2025

  Chain-of-thought (CoT) supervision can substantially improve transformer performance, yet the mechanisms by which models learn to follow and benefit from CoT remain poorly understood. We investigate these learning dynamics through the lens of grokking by pretraining transformers on symbolic reasonin…