arXiv:2602.22288v1 Announce Type: new Abstract: Sudden cardiac death (SCD) is unpredictable, and its prediction in Chagas cardiomyopathy (CC) remains a significant challenge, especially in patients not classified as high risk. While AI and machine learning models improve risk stratification, their…
arXiv:2602.22884v1 Announce Type: cross Abstract: Amortized Bayesian Inference (ABI) enables efficient posterior estimation using generative neural networks trained on simulated data, but often suffers from performance degradation under model misspecification. While self-consistency (SC) training on unlabeled empirical data can enhance…
arXiv:2602.22291v1 Announce Type: new Abstract: While prior work has focused on projecting adversarial examples back onto the manifold of natural data to restore safety, we argue that a comprehensive understanding of AI safety requires characterizing the unsafe regions themselves. This…
arXiv:2602.23006v1 Announce Type: cross Abstract: Simulating a Gaussian process requires sampling from a high-dimensional Gaussian distribution, which scales cubically with the number of sample locations. Spectral methods address this challenge by exploiting the Fourier representation, treating the spectral density as…
arXiv:2602.22293v1 Announce Type: new Abstract: River systems operate as inherently interconnected continuous networks, meaning river hydrodynamic simulation ought to be a systemic process. However, widespread hydrology data scarcity often restricts data-driven forecasting to isolated predictions. To achieve systemic simulation and…
arXiv:2602.23136v1 Announce Type: cross Abstract: Multimodal LLMs can process speech and images, but they cannot hear a speaker’s voice or see an object’s texture. We show this is not a failure of encoding: speaker identity, emotion, and visual attributes survive…
arXiv:2602.22294v1 Announce Type: new Abstract: Models operating on dynamic physiologic signals must distinguish benign, label-preserving variability from true concept change. Existing concept-drift frameworks are largely distributional and provide no principled guidance on how much a model’s internal representation may move…
arXiv:2602.23312v1 Announce Type: cross Abstract: Leader-follower interaction is an important paradigm in human-robot interaction (HRI). Yet, assigning roles in real time remains challenging for resource-constrained mobile and assistive robots. While large language models (LLMs) have shown promise for natural communication,…
arXiv:2505.17517v4 Announce Type: replace Abstract: We present a novel geometric perspective on the latent space of diffusion models. We first show that the standard pullback approach, utilizing the deterministic probability flow ODE decoder, is fundamentally flawed. It provably forces geodesics…
arXiv:2510.27480v2 Announce Type: replace Abstract: We propose a method for learning and sampling from probability distributions supported on the simplex. Our approach maps the open simplex to Euclidean space via smooth bijections, leveraging the Aitchison geometry to define the mappings,…
