digitado

arXiv:2604.14209v1 Announce Type: new Abstract: As deep neural networks are deployed in safety-critical domains such as autonomous driving and medical diagnosis, stakeholders need explanations that are interpretable but also trustworthy with formal guarantees. Existing XAI methods fall short: heuristic attribution techniques (e.g., LIME, Integrated Gradients) highlight influential features but offer no mathematical guarantees about decision boundaries, while formal methods verify robustness yet remain untargeted, analyzing the nearest boundary regardless of whether it represents a critical risk. In safety-critical […]

Ver mais

arXiv:2604.14207v1 Announce Type: new Abstract: In the initial deployment of large-scale distributed space systems using small satellites, achieving a reliable transition to passively stable orbits while maintaining inter-satellite distances within effective control and communication ranges is crucial, particularly given the presence of deployment errors and uncontrolled coasting phases. This study presents a framework for designing formation initialization that provides probabilistic safety guarantees. The scope covers the initial deployment phase, from sequential release by a single carrier to commissioning, […]

Ver mais

arXiv:2604.14206v1 Announce Type: new Abstract: This paper proposes a machine learning assisted portfolio optimization framework designed for low data environments and regime uncertainty. We construct a teacher student learning pipeline in which a Conditional Value at Risk (CVaR) optimizer generates supervisory labels, and neural models (Bayesian and deterministic) are trained using both real and synthetically augmented data. The synthetic data is generated using a factor based model with t copula residuals, enabling training beyond the limited real sample […]

Ver mais

arXiv:2604.14205v1 Announce Type: new Abstract: This paper brings cooperative protocols for multi-agent systems with agents having a finite state-space. Both scalar single-integrator consensus and general LTI systems synchronization are considered. Systems having a finite state-space describe agents with minimal memory capacity processing only a finite alphabet. Such systems are remarkably resilient to communication noise. The crucial problem, however, is to construct the admissible communication topology, which is NP-hard. We address this by efficiently exploring the subsets of admissible […]

Ver mais

arXiv:2604.14204v1 Announce Type: new Abstract: Multimodal emotion recognition in conversations aims to infer utterance-level emotions by jointly modeling textual, acoustic, and visual cues within context. Despite recent progress, key challenges remain, including redundant cross-modal information, imperfect semantic alignment, and insufficient modeling of high-order speaker interactions. To address these issues, we propose a framework that combines dual-space feature disentanglement with dual-branch graph learning. A shared encoder and modality-specific encoders are used to separate modality-invariant and modality-specific representations. The invariant […]

Ver mais

arXiv:2604.14203v1 Announce Type: new Abstract: In environments with uncertainties or undesirable influences, control systems can require additional energy to achieve their task while remaining resilient to these influences. In this paper, we present an energetic resilience metric that quantifies the maximal additional energy used by a system under undesired effects, while satisfying complex specifications encoded through temporal logic. We prove that this metric satisfies properties that enable its computation even for compositions of these specifications, thus allowing considerations […]

Ver mais

arXiv:2604.14198v1 Announce Type: new Abstract: Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimodal training recipes tune mixtures along a single dimension, typically data format or task type. We introduce MixAtlas, a method that produces benchmark-targeted data recipes that can be inspected, adapted, and transferred to new corpora. MixAtlas decomposes the training corpus along two axes: image concepts (10 visual-domain clusters discovered via CLIP embeddings) and task […]

Ver mais

arXiv:2604.14197v1 Announce Type: new Abstract: Large language model (LLM) performance depends heavily on prompt design, yet prompt construction is often described and applied inconsistently. Our purpose was to derive a reference framework for structuring LLM prompts. This paper presents PICCO, a framework derived through a rigorous synthesis of 11 previously published prompting frameworks identified through a multi-database search. The analysis yields two main contributions. First, it proposes a taxonomy that distinguishes prompt frameworks, prompt elements, prompt generation, prompting […]

Ver mais

arXiv:2604.14193v1 Announce Type: new Abstract: Human 3D vision involves two distinct stages: an Experience Module, where stereo depth is extracted relative to fixation, and an Inference Module, where this experience is interpreted to estimate 3D scene properties. Paradoxically, although our experience of stereo vision does not provide us with distance information, it does affect our inferences about visual scale. We propose the Inference Module exploits a natural scene statistic: near scenes produce vivid disparity gradients, while far scenes […]

Ver mais

arXiv:2604.14191v1 Announce Type: new Abstract: State Space Models (SSMs) such as Mamba have become a popular alternative to Transformer models, due to their reduced memory consumption and higher throughput at generation compared to their Attention-based counterparts. On the other hand, the community has built up a considerable body of knowledge on how to train Transformers, and many pretrained Transformer models are readily available. To facilitate the adoption of SSMs while leveraging existing pretrained Transformers, we aim to identify […]

Ver mais