digitado

arXiv:2603.25857v1 Announce Type: new Abstract: The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecular property prediction. However, their effectiveness in in-context learning remains ambiguous, particularly given the potential for training data contamination in widely used benchmarks. This paper investigates whether LLMs perform genuine in-context regression on molecular properties or rely primarily on memorized values. Furthermore, we analyze the interplay between pre-trained knowledge and in-context information through a series […]

Ver mais

arXiv:2603.25855v1 Announce Type: new Abstract: Genome-Wide Association Studies (GWAS) identify associations between genetic variants and disease; however, moving beyond associations to causal mechanisms is critical for therapeutic target prioritization. The recently proposed Knowledge Graph GWAS (KGWAS) framework addresses this challenge by linking genetic variants to downstream gene-gene interactions via a knowledge graph (KG), thereby improving detection power and providing mechanistic insights. However, the original KGWAS implementation relies on a large general-purpose KG, which can introduce spurious correlations. We […]

Ver mais

arXiv:2603.25853v1 Announce Type: new Abstract: This paper presents a system-level analytical framework for modeling and minimizing phase noise in body-biased cross-coupled LC-tank voltage-controlled oscillators (LC-VCOs). Building upon Impulse Sensitivity Function (ISF) theory, the impulse sensitivity and noise modulation mechanisms associated with both flicker and thermal noise sources are systematically characterized. By modeling the oscillator as a nonlinear dynamical system and incorporating transistor operation across multiple regions, analytical expressions for device-level noise power spectral densities (PSDs) are derived as […]

Ver mais

arXiv:2603.25852v1 Announce Type: new Abstract: The rising adoption of generative AI/ML technologies increases the need to support teens in developing AI/ML literacies. Child-computer interaction research argues that construction activities can support young people in understanding these systems and their implications. Recent exploratory studies demonstrate the feasibility of engaging teens in the construction of very small generative language models (LMs). However, it is unclear how constructing such models may foster the development of teens’ understanding of these systems from […]

Ver mais

arXiv:2603.25841v1 Announce Type: new Abstract: Current multimodal large language models (MLLMs) cannot effectively utilize eye-gaze information for video understanding, even when gaze cues are supplied via visual overlays or text descriptions. We introduce GazeQwen, a parameter efficient approach that equips an open-source MLLM with gaze awareness through hidden-state modulation. At its core is a compact gaze resampler (~1-5 M trainable parameters) that encodes V-JEPA 2.1 video features together with fixation-derived positional encodings and produces additive residuals injected into […]

Ver mais

arXiv:2603.25840v1 Announce Type: new Abstract: This paper studies system identification for nonlinear state-space models, a problem that arises across many fields yet remains challenging in practice. Focusing on maximum likelihood estimation, we employ Bayesian optimization (BayesOpt) to address this problem by leveraging its derivative-free global search capability enabled by surrogate modeling of the likelihood function. Despite these advantages, standard BayesOpt often suffers from slow convergence, high computational cost, and practical difficulty in attaining global optima under limited computational […]

Ver mais

arXiv:2603.25839v1 Announce Type: new Abstract: Deep neural networks exhibit a simplicity bias, a well-documented tendency to favor simple functions over complex ones. In this work, we cast new light on this phenomenon through the lens of the Minimum Description Length principle, formalizing supervised learning as a problem of optimal two-part lossless compression. Our theory explains how simplicity bias governs feature selection in neural networks through a fundamental trade-off between model complexity (the cost of describing the hypothesis) and […]

Ver mais

arXiv:2603.25836v1 Announce Type: new Abstract: In low-resource multilingual speech-to-text translation, uniform architectural sharing across languages frequently introduces representation conflicts that impede convergence. This work proposes a principled methodology to automatically determine layer-specific sharing patterns by mining training gradient information. Our approach employs three distinct analysis strategies: distance-based language clustering, self/cross-task divergence metrics for capacity allocation, and joint factorization coupled with canonical correlation analysis for subspace alignment. Extensive evaluation across four language pairs (using the SeamlessM4T-Medium architecture) demonstrates persistent […]

Ver mais

arXiv:2603.25835v1 Announce Type: new Abstract: Starlink has rapidly emerged as the world’s largest satellite constellation and the de facto reference system for low Earth orbit (LEO) networking research. Existing literature predominantly models Starlink as a static, symmetric, and fully deployed structure with uniformly distributed satellites. However, we reveal that Starlink’s actual deployment, orbital configurations, and operational dynamics fundamentally deviate from these idealized assumptions. Leveraging satellite observation data spanning 2019 to 2025, we demonstrate that the constellation is highly […]

Ver mais

arXiv:2603.25834v1 Announce Type: new Abstract: Recent advances in parallel computing and GPU acceleration have created new opportunities for computation-intensive learning problems such as Active SLAM — where actions are selected to reduce uncertainty and improve joint mapping and localization. However, existing DRL-based approaches remain constrained by the lack of scalable parallel training. In this work, we address this challenge by proposing a scalable end-to-end DRL framework for Active SLAM that enables massively parallel training. Compared with the state […]

Ver mais