arXiv:2604.06995v1 Announce Type: new
Abstract: Existing Graphical User Interface (GUI) reasoning tasks remain challenging, particularly in UI understanding. Current methods typically rely on direct screen-based decision-making, which lacks interpreta…
arXiv:2604.06620v1 Announce Type: new
Abstract: Quantitative estimation of wheel polygonal roughness from axle-box vibration signals is a challenging yet practically relevant problem for rail-vehicle condition monitoring. Existing studies have largely…
arXiv:2412.04880v3 Announce Type: replace
Abstract: Influenced by the complexity of volumetric imaging, there is a shortage of established datasets useful for benchmarking volumetric deep-learning models. As a consequence, new and existing models are …
arXiv:2604.06279v1 Announce Type: cross
Abstract: Accurate parameter selection is fundamental to gyrokinetic plasma simulations, yet current practices rely heavily on manual literature reviews, leading to inefficiencies and inconsistencies. We introdu…
arXiv:2602.03604v3 Announce Type: replace-cross
Abstract: We present EB-JEPA, an open-source library for learning representations and world models using Joint-Embedding Predictive Architectures (JEPAs). JEPAs learn to predict in representation space r…
arXiv:2604.06684v1 Announce Type: new
Abstract: Clinical Reasoning on Electronic Health Records (EHRs) is a fundamental yet challenging task in modern healthcare. While in-context learning (ICL) offers a promising inference-time adaptation paradigm fo…
arXiv:2604.06916v1 Announce Type: cross
Abstract: Reinforcement-Learning-based post-training has recently emerged as a promising paradigm for aligning text-to-image diffusion models with human preferences. In recent studies, increasing the rollout gro…
arXiv:2604.07345v1 Announce Type: cross
Abstract: The rapid growth of generative artificial intelligence (AI) has introduced unprecedented computational demands, driving significant increases in the energy footprint of data centers. However, existing …
arXiv:2604.06808v1 Announce Type: cross
Abstract: This paper presents CBM-Dual, the first silicon-proven digital chaotic dynamics processor (CDP) supporting both simulated annealing (SA) and reservoir computing (RC). CBM-Dual enables real-time decisio…
arXiv:2604.06753v1 Announce Type: new
Abstract: When an LLM-based agent improves on a task, is the gain from the model itself or from the reasoning paradigm wrapped around it? We study this question by comparing six inference-time paradigms, namely Di…