arXiv:2601.03320v1 Announce Type: new Abstract: On-policy reinforcement learning (RL), particularly Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), has become the dominant paradigm for fine-tuning large language models (LLMs). While policy ratio clipping stabilizes training, this heuristic hard…
arXiv:2601.03988v1 Announce Type: cross Abstract: Background: Extracting the stages that structure Machine Learning (ML) pipelines from source code is key for gaining a deeper understanding of data science practices. However, the diversity caused by the constant evolution of the ML…
arXiv:2601.03367v1 Announce Type: new Abstract: Understanding and modeling the constitutive behavior of concrete is crucial for civil and defense applications, yet widely used phenomenological models such as Karagozian & Case concrete (KCC) model depend on empirically calibrated failure surfaces that…
arXiv:2601.04163v1 Announce Type: cross Abstract: Pathology foundation models (PFMs) have become central to computational pathology, aiming to offer general encoders for feature extraction from whole-slide images (WSIs). Despite strong benchmark performance, PFM robustness to real-world technical domain shifts, such as…
arXiv:2601.03375v1 Announce Type: new Abstract: Convolutional Neural Networks (CNNs) have shown promising results in efficiency and accuracy in image classification. However, their efficacy often relies on large, labeled datasets, posing challenges for applications with limited data availability. Our research addresses…
arXiv:2504.05695v4 Announce Type: replace Abstract: We prove that overparametrized neural networks are able to generalize with a test error that is independent of the level of overparametrization, and independent of the Vapnik-Chervonenkis (VC) dimension. We prove explicit bounds that only…
arXiv:2601.03376v1 Announce Type: new Abstract: This paper presents a novel framework to accelerate route prediction in Drone-as-a-Service operations through weather-aware deep learning models. While classical path-planning algorithms, such as A* and Dijkstra, provide optimal solutions, their computational complexity limits real-time…
arXiv:2510.09668v2 Announce Type: replace Abstract: Drug-drug interactions (DDIs) are a leading cause of preventable adverse events, often complicating treatment and increasing healthcare costs. At the same time, knowing which drugs do not interact is equally important, as such knowledge supports…
arXiv:2601.03385v1 Announce Type: new Abstract: The rapid adoption of synthetic data for training Large Language Models (LLMs) has introduced the technical challenge of “model collapse”-a degenerative process where recursive training on model-generated content leads to a contraction of distributional variance…
arXiv:2601.00834v2 Announce Type: replace Abstract: Simulating nonlinear reaction-diffusion dynamics on complex, non-Euclidean manifolds remains a fundamental challenge in computational morphogenesis, constrained by high-fidelity mesh generation costs and symplectic drift in discrete time-stepping schemes. This study introduces the Intrinsic-Metric Physics-Informed Neural…
