Modern forward electrocardiogram (ECG) computational models rely on an accurate representation of the torso domain. The lead-field method enables fast ECG simulations while preserving full geometric fidelity. Achieving high anatomical accuracy in torso representation is, however, challenging in clinical practice, as imaging protocols are typically focused on the heart and often do not include the entire torso. In addition, the computational cost of the lead-field method scales linearly with the number of electrodes, limiting its applicability in high-density […]

Ver mais

Sometimes there come a time in your career when you want to take the next step in your development, but you may not be sure what that next step is or what opportunities it will open up for you. I like the quote: Life can only be understood backwards, but it must be lived forwards. Kierkegaard On my way I decided to choose Robolectric and answer my questions about the structure of a library with an ambiguous reputation, […]

Ver mais

arXiv:2603.20293v1 Announce Type: new Abstract: Text-attributed graphs, where nodes are enriched with textual attributes, have become a powerful tool for modeling real-world networks such as citation, social, and transaction networks. However, existing methods for learning from these graphs often assume that the distributions of training and testing data are consistent. This assumption leads to significant performance degradation when faced with out-of-distribution (OOD) data. In this paper, we address the challenge of node-level OOD detection in text-attributed graphs, with […]

Ver mais

This paper deals with some expressions of the fractional generalized Gronwall inequality when associated with both non-negative and non-positive singular kernels and establishes sharp Mittag- Leffler bounds containing different ingredients. The long-term behavior of non-autonomous fractional order systems by means of modified fractional Lyapunov theorems is analyzed. As an application, we give a few examples that use quadratic Lyapunov functions for typical fractional order systems to predict trajectories that ultimately aim to reach vector 0 as t → […]

Ver mais

Introduction: The Cage We Built and Called Progress Humanity has achieved something historically unprecedented: it has constructed the most sophisticated cage ever devised, decorated it with infinite scrolling and dopamine-triggering notifications, and voluntarily imprisoned itself within it — celebrating every new feature as liberation while surrendering the last remnants of digital sovereignty with every click. The internet — that magnificent, anarchic, boundless frontier of human imagination — has been systematically dismembered, consolidated, and weaponized by a handful of […]

Ver mais

arXiv:2410.04264v3 Announce Type: replace Abstract: Dynamic feature transformation (the rich regime) does not always align with predictive performance (better representation), yet accuracy is often used as a proxy for richness, limiting analysis of their relationship. We propose a computationally efficient, performance-independent metric of richness grounded in the low-rank bias of rich dynamics, which recovers neural collapse as a special case. The metric is empirically more stable than existing alternatives and captures known lazy-torich transitions (e.g., grokking) without relying […]

Ver mais

arXiv:2406.01552v2 Announce Type: replace Abstract: Tensors are a fundamental data structure for many scientific contexts, such as time series analysis, materials science, and physics, among many others. Improving our ability to produce and handle tensors is essential to efficiently address problems in these domains. In this paper, we show how to exploit the underlying symmetries of functions that map tensors to tensors. More concretely, we develop universally expressive equivariant machine learning architectures on tensors that exploit that, in […]

Ver mais

Leveraging representation encoders for generative modeling offers a path for efficient, high-fidelity synthesis. However, standard diffusion transformers fail to converge on these representations directly. While recent work attributes this to a capacity bottleneck proposing computationally expensive width scaling of diffusion transformers we demonstrate that the failure is fundamentally geometric. We identify Geometric Interference as the root cause: standard Euclidean flow matching forces probability paths through the low-density interior of the hyperspherical feature space of representation encoders, rather than […]

Ver mais

arXiv:2603.25934v1 Announce Type: cross Abstract: In this work, we investigate how to develop sharp concentration inequalities for sub-Weibull random variables, including sub-Gaussian and sub-exponential distributions. Although the random variables may not be sub-Guassian, the tail probability around the origin behaves as if they were sub-Gaussian, and the tail probability decays align with the Orlicz $Psi_alpha$-tail elsewhere. Specifically, for independent and identically distributed (i.i.d.) ${X_i}_{i=1}^n$ with finite Orlicz norm $|X|_{Psi_alpha}$, our theory unveils that there is an interesting phase […]

Ver mais

arXiv:2601.08010v1 Announce Type: new Abstract: Vision-language models achieve strong performance across a wide range of multimodal understanding and reasoning tasks, yet their multi-step reasoning remains unstable. Repeated sampling over the same input often produces divergent reasoning trajectories and inconsistent final predictions. To address this, we introduce two complementary approaches inspired by test-time scaling: (1) CASHEW, an inference-time framework that stabilizes reasoning by iteratively aggregating multiple candidate trajectories into higher-quality reasoning traces, with explicit visual verification filtering hallucinated steps […]

Ver mais