Fuzzy, Symbolic, and Contextual: Enhancing LLM Instruction via Cognitive Scaffolding
arXiv:2508.21204v1 Announce Type: new Abstract: We study how architectural inductive biases influence the cognitive behavior of large language models (LLMs)…
Arbitrary Precision Printed Ternary Neural Networks with Holistic Evolutionary Approximation
arXiv:2508.19660v2 Announce Type: replace-cross Abstract: Printed electronics offer a promising alternative for applications beyond silicon-based systems, requiring properties like flexibility,…
On the Hardness of Learning GNN-based SAT Solvers: The Role of Graph Ricci Curvature
arXiv:2508.21513v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) have recently shown promise as solvers for Boolean Satisfiability Problems (SATs)…
Robustness is Important: Limitations of LLMs for Data Fitting
arXiv:2508.19563v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are being applied in a wide array of settings, well beyond…
ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation
arXiv:2508.20131v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical…
HPC Digital Twins for Evaluating Scheduling Policies, Incentive Structures and their Impact on Power and Cooling
arXiv:2508.20016v2 Announce Type: replace-cross Abstract: Schedulers are critical for optimal resource utilization in high-performance computing. Traditional methods to evaluate schedulers…