arXiv:2508.13990v2 Announce Type: replace Abstract: Multidimensional data is often associated with uncertainties that are not well-described by normal distributions. In this work, we describe how such distributions can be projected to a low-dimensional space using uncertainty-aware principal component analysis (UAPCA). We propose to model multidimensional distributions using Gaussian mixture models (GMMs) and derive the projection from a general formulation that allows projecting arbitrary probability density functions. The low-dimensional projections of the densities exhibit more details about the distributions […]

Ver mais

Early identification of patients at risk for clinical deterioration in the intensive care unit (ICU) remains a critical challenge. Delayed recognition of impending adverse events, including mortality, vasopressor initiation, and mechanical ventilation, contributes to preventable morbidity and mortality. We present a multimodal deep learning approach that combines structured time-series data (vital signs and laboratory values) with unstructured clinical notes to predict patient deterioration within 24 hours. Using the MIMIC-IV database, we constructed a cohort of 74,822 ICU stays […]

Ver mais

Gradient inversion attacks threaten client privacy in federated learning by reconstructing training samples from clients’ shared gradients. Gradients aggregate contributions from multiple records and existing attacks may fail to disentangle them, yielding incorrect reconstructions with no intrinsic way to certify success. In vision and language, attackers may fall back on human inspection to judge reconstruction plausibility, but this is far less feasible for numerical tabular records, fueling the impression that tabular data is less vulnerable. We challenge this […]

Ver mais

arXiv:2603.08886v1 Announce Type: new Abstract: We study a class of finite-state channels, known as POST channels, in which the previous channel output serves as the current state. A POST channel is deemed approximately memoryless when the state-dependent transition matrices are sufficiently close to one another. For this family of channels, under a surjectivity condition on the associated memoryless reference channel, we show that the feedback capacity coincides with the non-feedback capacity. Consequently, for almost all approximately memoryless POST […]

Ver mais

Monotone optimisation problems admit specialised global solvers such as the Polyblock Outer Approximation (POA) algorithm, but these methods typically require explicit objective and constraint functions. In many applications, these functions are only available through data, making POA difficult to apply directly. We introduce an algorithm-aware learning approach that integrates learned models into POA by directly predicting its projection primitive via the radial inverse, avoiding the costly bisection procedure used in standard POA. We propose Homogeneous-Monotone Radial Inverse (HM-RI) […]

Ver mais

As has been said by many commentators, rare earths are not particularly rare.  Via source, here is an estimate of their abundance in the Earth’s surface: Note by the way the Y-axis is logarithmic so small changes in vertical position can mean a factor of 10 or more difference in concentration.  But the rare earths are not unreasonably far off fairly common industrial metals like lead, nickel, copper, and molybdenum and well more common than gold, silver, and […]

Ver mais

arXiv:2604.09729v2 Announce Type: new Abstract: Short-form video platforms have become central to multimedia information dissemination, where comments play a critical role in driving engagement, propagation, and algorithmic feedback. However, existing approaches — including video summarization and live-streaming danmaku generation — fail to produce authentic comments that conform to platform-specific cultural and linguistic norms. In this paper, we present LOLGORITHM, a novel modular multi-agent framework for stylized short-form video comment generation. LOLGORITHM supports six controllable comment styles and comprises […]

Ver mais

Large language models have achieved significant reasoning improvements through reinforcement learning with verifiable rewards (RLVR). Yet as model capabilities grow, constructing high-quality reward signals becomes increasingly difficult, making it essential to understand when RLVR can succeed under weaker forms of supervision. We conduct a systematic empirical study across diverse model families and reasoning domains under three weak supervision settings: scarce data, noisy rewards, and self-supervised proxy rewards. We find that generalization is governed by training reward saturation dynamics: […]

Ver mais