digitado

arXiv:2604.08630v1 Announce Type: new Abstract: We study differentially private data release, where a database is accessed through successive, possibly adaptive queries and mechanisms. Existing composition theorems and privacy filters combine worst case per-round privacy parameters, leaving room for more refined accounting based on realised leakage, which we term realisation-level accounting. We propose a realisation-level filtering approach to determine stopping times for data releases, and design one such filter. Despite technical challenges arising from conditioning on realisations and stopping […]

Ver mais

arXiv:2604.08628v1 Announce Type: new Abstract: Unauthorized disclosure of confidential documents demands robust, low-leakage classification. In real work environments, there is a lot of inflow and outflow of documents. To continuously update knowledge, we propose a methodology for classifying confidential documents using Retrieval Augmented Classification (RAC). To confirm this effectiveness, we compare RAC and supervised fine tuning (FT) on the WikiLeaks US Diplomacy corpus under realistic sequence-length constraints. On balanced data, RAC matches FT. On unbalanced data, RAC is […]

Ver mais

arXiv:2604.08627v1 Announce Type: new Abstract: Pretrained models have become standard in both vision and language, yet they typically do not provide reliable measures of confidence. Existing uncertainty estimation methods, such as deep ensembles and MC dropout, are often too computationally expensive to deploy in practice. Evidential Deep Learning (EDL) offers a more efficient alternative, but it requires models to be trained to output evidential quantities from the start, which is rarely true for pretrained networks. To enable EDL-style […]

Ver mais

arXiv:2604.08626v1 Announce Type: new Abstract: Understanding objects in 3D from a single image is a cornerstone of spatial intelligence. A key step toward this goal is monocular 3D object detection–recovering the extent, location, and orientation of objects from an input RGB image. To be practical in the open world, such a detector must generalize beyond closed-set categories, support diverse prompt modalities, and leverage geometric cues when available. Progress is hampered by two bottlenecks: existing methods are designed for […]

Ver mais

arXiv:2604.08624v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) are naturally suited for speech processing tasks due to their specific dynamics, which allows them to handle temporal data. However, the threshold-based generation of spikes in SNNs intuitively causes an angular or irregular predictive landscape. We explore the effect of using the Bayesian learning approach for the weights on the irregular predictive landscape. For the surrogate-gradient SNNs, we also explore the application of the Improved Variational Online Newton (IVON) […]

Ver mais

arXiv:2604.08621v1 Announce Type: new Abstract: In consumer applications, Customer Relationship Management (CRM) has traditionally relied on the manual optimisation of static, rule-based messaging strategies. While adaptive and autonomous learning systems offer the promise of scalable personalisation, it remains unclear to what extent “human-in-the-loop” oversight is required to sustain performance uplift over time. This paper presents a longitudinal case study analysing a real-world consumer application that leverages agentic infrastructure to personalise marketing messaging for a large-scale user base over […]

Ver mais

arXiv:2604.08620v1 Announce Type: new Abstract: Reinforcement learning is typically treated as a uniform, data-driven optimization process, where updates are guided by rewards and temporal-difference errors without explicitly exploiting global structure. In contrast, dynamic programming methods rely on structured information propagation, enabling efficient and stable learning. In this paper, we provide evidence that such structure can be recovered from the learning dynamics of distributional reinforcement learning. By analyzing the temporal evolution of return distributions, we identify signals that capture […]

Ver mais

arXiv:2604.08619v1 Announce Type: new Abstract: This paper presents a comprehensive dataset of doctoral theses defended in France between 1985 and 2025, constructed from multiple national academic metadata sources. The dataset is primarily based on data from the French national thesis platform and is enriched using additional authority and bibliographic databases to improve data quality, completeness, and interoperability. The data production pipeline includes the aggregation of heterogeneous sources, the correction of inconsistent identifiers, the enrichment of person and institution […]

Ver mais

arXiv:2604.08618v1 Announce Type: new Abstract: Deploying LLM-powered agents in enterprise scenarios such as cloud technical support demands high-quality, domain-specific skills. However, existing skill creators lack domain grounding, producing skills poorly aligned with real-world task requirements. Moreover, once deployed, there is no systematic mechanism to trace execution failures back to skill deficiencies and drive targeted refinements, leaving skill quality stagnant despite accumulating operational evidence. We introduce SkillForge, a self-evolving framework that closes an end-to-end creation-evaluation-refinement loop. To produce well-aligned […]

Ver mais

arXiv:2604.08617v1 Announce Type: new Abstract: Exemplar replay has become an effective strategy for mitigating catastrophic forgetting in federated continual learning (FCL) by retaining representative samples from past tasks. Existing studies focus on designing sample-importance estimation mechanisms to identify information-rich samples. However, they typically overlook strategies for effectively utilizing the selected exemplars, which limits their performance under continual dynamic heterogeneity across clients and tasks. To address this issue, this paper proposes a Federated gEometry-Aware correcTion method, termed FEAT, which […]

Ver mais