arXiv:2406.17002v4 Announce Type: replace-cross Abstract: Artificial intelligence applied to electrocardiography (AI-ECG) shows potential for mortality prediction, but heterogeneous approaches and private datasets have limited generalizable insights. To address this, we systematically evaluated model design choices across three large cohorts: Beth…
arXiv:2509.10000v1 Announce Type: new Abstract: Neural scaling laws–power-law relationships between generalization errors and characteristics of deep learning models–are vital tools for developing reliable models while managing limited resources. Although the success of large language models highlights the importance of these…
arXiv:2412.19087v2 Announce Type: replace-cross Abstract: Soft prompt learning methods are effective for adapting vision-language models (VLMs) to downstream tasks. Nevertheless, empirical evidence reveals a tendency of existing methods that they overfit seen classes and exhibit degraded performance on unseen classes.…
arXiv:2509.10011v1 Announce Type: new Abstract: This paper introduces the Intrinsic Dimension Estimating Autoencoder (IDEA), which identifies the underlying intrinsic dimension of a wide range of datasets whose samples lie on either linear or nonlinear manifolds. Beyond estimating the intrinsic dimension,…
arXiv:2505.08159v3 Announce Type: replace-cross Abstract: Machine learning interatomic potentials have revolutionized complex materials design by enabling rapid exploration of material configurational spaces via crystal structure prediction with ab initio accuracy. However, critical challenges persist in ensuring robust generalization to unknown…
arXiv:2509.10025v1 Announce Type: new Abstract: Understanding the internal organization of neural networks remains a fundamental challenge in deep learning interpretability. We address this challenge by exploring a novel Sparse Mixture of Experts Variational Autoencoder (SMoE-VAE) architecture. We test our model…
arXiv:2507.13024v2 Announce Type: replace-cross Abstract: Predicting a response with partially missing inputs remains a challenging task even in parametric models, since parameter estimation in itself is not sufficient to predict on partially observed inputs. Several works study prediction in linear…
arXiv:2509.10033v1 Announce Type: new Abstract: Sparse dictionary coding represents signals as linear combinations of a few dictionary atoms. It has been applied to images, time series, graph signals and multi-way spatio-temporal data by jointly employing temporal and spatial dictionaries. Data-agnostic…
arXiv:2509.08972v2 Announce Type: replace-cross Abstract: The increasing reliance on generative AI models has accelerated the generation rate of synthetic data, with some projections suggesting that most available new data for training could be machine-generated by 2030. This shift to a…
arXiv:2509.10034v1 Announce Type: new Abstract: We present a formal and constructive theory showing that probabilistic finite automata (PFAs) can be exactly simulated using symbolic feedforward neural networks. Our architecture represents state distributions as vectors and transitions as stochastic matrices, enabling…
