Related papers: Working Paper: Towards Schema-based Learning from …

Computer science education has been at the heart of Scheme from the beginning. The language was designed in the 1970s concurrently with the MIT course 6.001 and the textbook "Structure and Interpretation of Computer Programs" (SICP). To…

Autoregressive language models achieve remarkable performance, yet a unified theory explaining their internal mechanisms, how training shapes representations, and why these representations support complex behavior remains incomplete. We…

Understanding and reasoning over complex spreadsheets remain fundamental challenges for large language models (LLMs), which often struggle with accurately capturing the complex structure of tables and ensuring reasoning correctness. In this…

Neural memory enables fast adaptation to new tasks with just a few training samples. Existing memory models store features only from the single last layer, which does not generalize well in presence of a domain shift between training and…

Despite significant progress in natural language understanding, Large Language Models (LLMs) remain error-prone when performing logical reasoning, often lacking the robust mental representations that enable human-like comprehension. We…

In this paper, we propose supervised dictionary learning (SDL) by incorporating information on class labels into the learning of the dictionary. To this end, we propose to learn the dictionary in a space where the dependency between the…

This paper has proposed a Graph - semantic based conceptual model for semi-structured database system, called GOOSSDM, to conceptualize the different facets of such system in object oriented paradigm. The model defines a set of graph based…

In this paper we obtain several model structures on {\bf DblCat}, the category of small double categories. Our model structures have three sources. We first transfer across a categorification-nerve adjunction. Secondly, we view double…

Continual learning is crucial for creating AI agents that can learn and improve themselves autonomously. A primary challenge in continual learning is to learn new tasks without losing previously learned knowledge. Current continual learning…

Understanding learning as a dynamic process is challenging due to the interaction of multiple factors, including cognitive load, internal state change, and subjective evaluation. Existing approaches often address these elements in…

Large language model (LLM) agents increasingly rely on reusable skills: capability packages that combine instructions, control flow, constraints, and tool calls. In current agent systems, however, skills are still represented by text-heavy…

Decision-making is challenging in robotics environments with continuous object-centric states, continuous actions, long horizons, and sparse feedback. Hierarchical approaches, such as task and motion planning (TAMP), address these…

Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w.r.t model's generalizability, performance, and training/inference memory footprint. The aforementioned benefits become…

Scene Graph Generation (SGG) structures visual scenes as graphs of objects and their relations. While Multimodal Large Language Models (MLLMs) have advanced end-to-end SGG, current methods are hindered by both a lack of task-specific…

Sub-symbolic artificial intelligence methods dominate the fields of environment-type classification and Simultaneous Localisation and Mapping. However, a significant area overlooked within these fields is solution transparency for the…

This paper proposes a novel scalable community-based neural framework for graph learning. The framework learns the graph topology through the task of community detection and link prediction by optimizing with our proposed joint SBM loss…

This study examines the relationship between speech representations and the hierarchical structure of cognitive assessment in mild cognitive impairment. Utilizing 5,754 German neuropsychological assessment recordings, we evaluate six…

Multimodal reasoning in vision-language models (VLMs) typically relies on a two-stage process: supervised fine-tuning (SFT) and reinforcement learning (RL). In standard SFT, all tokens contribute equally to the loss, even though reasoning…

Creative and communicative work is often underpinned by implicit structures, such as the Hero's Journey in storytelling, design patterns in software, or chord progressions in music. People often learn these structures from examples - a…

Learning analytics systems increasingly integrate large language models (LLMs) to provide adaptive scaffolding in complex learning environments, yet personalization is often driven by global instructional choices rather than principled…