arXiv:2602.04364v1 Announce Type: new Abstract: Prediction sets provide a means of quantifying the uncertainty in predictive tasks. Using held out calibration data, conformal prediction and risk control can produce prediction sets that exhibit statistically valid error control in a computationally efficient manner. However, in the standard formulations, the error is only controlled on average over many possible calibration datasets of fixed size. In this paper, we extend the control to remain valid with high probability over a cumulatively […]

Ver mais

arXiv:2601.08316v1 Announce Type: cross Abstract: Deep double descent is one of the key phenomena underlying the generalization capability of deep learning models. In this study, epoch-wise double descent, which is delayed generalization following overfitting, was empirically investigated by focusing on the evolution of internal structures. Fully connected neural networks of three different sizes were trained on the CIFAR-10 dataset with 30% label noise. By decomposing the loss curves into signal contributions from clean and noisy training data, the […]

Ver mais

As someone who works in or around the creative industries, you probably nod along when you hear that AI is “transforming the space.” Everyone talks about disruption, new workflows, the death of certain roles. Everyone is on the same page. But last week I was at a closed-door meeting — platform owners, startup founders, production studio heads. The kind of people who talk about transformation at conferences and talk about margins among themselves. And the conversation was different. […]

Ver mais

arXiv:2601.21001v1 Announce Type: new Abstract: This paper introduces the Interactive Memory Archive (IMA), a conceptual framework for AI-mediated reminiscence designed to support cognitive en-gagement among older adults experiencing memory loss. IMA integrates multimodal sensing, natural language conversational scaffolding, and cloud-based archiving within the familiar form of a large format historical picture book. The model theorizes reminiscence as a guided, context-aware interaction eliciting autobiographical memories and preserving them as cul-tural artifacts. The paper positions IMA as a theoretical contribution, […]

Ver mais

arXiv:2602.18506v1 Announce Type: new Abstract: We initiate the study of control in hedonic games, where an external actor influences coalition formation by adding or deleting agents. We consider three basic control goals (1) enforcing that an agent is not alone (NA); (2) enforcing that a pair of agents is in the same coalition (PA); (3) enforcing that all agents are in the same grand coalition (GR), combined with two control actions: adding agents (AddAg) or deleting agents (DelAg). […]

Ver mais

arXiv:2603.07409v1 Announce Type: cross Abstract: Measurement error is prevalent across all domains of scientific research where only imprecise observations, rather than the true underlying values, can be obtained. For example, estimates of human microbiome diversity are based on small samples from a much larger, generally unobserved system and reflect both sampling error and technical variation. In high-noise settings like these, it becomes difficult to make accurate predictions and to summarize uncertainty. Methods have previously been proposed to accommodate […]

Ver mais

arXiv:2602.02619v1 Announce Type: new Abstract: While Large Language Models (LLMs) excel at short-term tasks, scaling them to long-horizon agentic workflows remains challenging. The core bottleneck lies in the scarcity of training data that captures authentic long-dependency structures and cross-stage evolutionary dynamics–existing synthesis methods either confine to single-feature scenarios constrained by model distribution, or incur prohibitive human annotation costs, failing to provide scalable, high-quality supervision. We address this by reconceptualizing data synthesis through the lens of real-world software evolution. […]

Ver mais

arXiv:2601.02366v1 Announce Type: new Abstract: Graph-based recommendation has achieved great success in recent years. The classical graph recommendation model utilizes ID embedding to store essential collaborative information. However, this ID-based paradigm faces challenges in transferring to a new domain, making it hard to build a pre-trained graph recommendation model. This phenomenon primarily stems from two inherent challenges: (1) the non-transferability of ID embeddings due to isolated domain-specific ID spaces, and (2) structural incompatibility between heterogeneous interaction graphs across […]

Ver mais

arXiv:2602.09246v1 Announce Type: new Abstract: The integration of Artificial Intelligence (AI) into Higher Education Institutions (HEIs) in Ecuador is not a technological option but a strategic imperative to prevent institutional obsolescence and academic irrelevance in Latin America. This paper presents the IA593 Framework, a governance, ethics, and operational model designed for the Universidad Nacional de Loja (UNL) and scalable as a reference for the Ecuadorian higher education system. The current context reveals a critical urgency: the Latin American […]

Ver mais