Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS
arXiv:2508.14313v2 Announce Type: replace-cross Abstract: Test-time scaling (TTS) for large language models (LLMs) has thus far fallen into two largely…
A Systematic Study of Deep Learning Models and xAI Methods for Region-of-Interest Detection in MRI Scans
arXiv:2508.14151v2 Announce Type: replace-cross Abstract: Magnetic Resonance Imaging (MRI) is an essential diagnostic tool for assessing knee injuries. However, manual…
LoUQAL: Low-fidelity informed Uncertainty Quantification for Active Learning in the chemical configuration space
arXiv:2508.15577v1 Announce Type: cross Abstract: Uncertainty quantification is an important scheme in active learning techniques, including applications in predicting quantum…
Are Virtual DES Images a Valid Alternative to the Real Ones?
arXiv:2508.15594v1 Announce Type: cross Abstract: Contrast-enhanced spectral mammography (CESM) is an imaging modality that provides two types of images, commonly…
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
arXiv:2508.14444v2 Announce Type: replace-cross Abstract: We introduce Nemotron-Nano-9B-v2, a hybrid Mamba-Transformer language model designed to increase throughput for reasoning workloads…
A Fully Spectral Neuro-Symbolic Reasoning Architecture with Graph Signal Processing as the Computational Backbone
arXiv:2508.14923v1 Announce Type: new Abstract: We propose a fully spectral, neuro-symbolic reasoning architecture that leverages Graph Signal Processing (GSP) as…