arXiv:2512.18209v5 Announce Type: replace Abstract: Empirical power–law scaling has been widely observed across modern deep learning systems, yet its theoretical origins and scope of validity remain incompletely understood. The Generalized Resolution–Shell Dynamics (GRSD) framework models learning as spectral energy transport…
arXiv:2601.07898v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently developed new advanced functionalities. Their effectiveness relies on statistical learning and generalization capabilities. However, they face limitations in internalizing the data they process and struggle, for instance, to autonomously…
arXiv:2601.07903v1 Announce Type: new Abstract: The World Wide Web needs reliable predictive capabilities to respond to changes in user behavior and usage patterns. Time series forecasting (TSF) is a key means to achieve this goal. In recent years, the large…
arXiv:2510.00282v2 Announce Type: replace-cross Abstract: In this work, we introduce a non-local five-moment electron pressure tensor closure parametrized by a Fully Convolutional Neural Network (FCNN). Electron pressure plays an important role in generalized Ohm’s law, competing with electron inertia. This…
arXiv:2601.07930v1 Announce Type: new Abstract: Functional group replacement is a pivotal approach in cheminformatics to enable the design of novel chemical compounds with tailored properties. Traditional methods for functional group removal and replacement often rely on rule-based heuristics, which can…
arXiv:2601.08539v1 Announce Type: cross Abstract: The rapid growth of AI has fueled the expansion of accelerator- or GPU-based data centers. However, the rising operational energy consumption has emerged as a critical bottleneck and a major sustainability concern. Dynamic Voltage and…
arXiv:2601.07935v1 Announce Type: new Abstract: The rapid evolution of Large Language Models (LLMs) has shifted focus from general-purpose capabilities to domain-specific expertise. However, adapting LLMs to specialized fields such as medicine presents two challenge: (1) the “Stability-Plasticity Dilemma”, where the…
arXiv:2601.08654v1 Announce Type: cross Abstract: The LLM-as-a-Judge paradigm promises scalable rubric-based evaluation, yet aligning frozen black-box models with human standards remains a challenge due to inherent generation stochasticity. We reframe judge alignment as a criteria transfer problem and isolate three…
arXiv:2601.07946v1 Announce Type: new Abstract: Data-driven flow-field reconstruction typically relies on autoencoder architectures that compress high-dimensional states into low-dimensional latent representations. However, classical approaches such as variational autoencoders (VAEs) often struggle to preserve the higher-order statistical structure of fluid flows…
arXiv:2601.08808v1 Announce Type: cross Abstract: Large language models often solve complex reasoning tasks more effectively with Chain-of-Thought (CoT), but at the cost of long, low-bandwidth token sequences. Humans, by contrast, often reason softly by maintaining a distribution over plausible next…
