arXiv:2510.06106v1 Announce Type: cross Abstract: Deep neural networks have achieved remarkable success, yet our understanding of how they learn remains limited. These models can learn high-dimensional tasks, which is generally statistically intractable due to the curse of dimensionality. This apparent…
arXiv:2508.13703v2 Announce Type: replace-cross Abstract: Existing research on single-machine scheduling is largely focused on exact algorithms, which perform well on typical instances but can significantly deteriorate on certain regions of the problem space. In contrast, data-driven approaches provide strong and…
arXiv:2510.06091v1 Announce Type: cross Abstract: Mixtures of linear dynamical systems (MoLDS) provide a path to model time-series data that exhibit diverse temporal dynamics across trajectories. However, its application remains challenging in complex and noisy settings, limiting its effectiveness for neural…
arXiv:2412.06438v2 Announce Type: replace-cross Abstract: Foundation models excel at single-turn reasoning but struggle with multi-turn exploration in dynamic environments, a requirement for many real-world challenges. We evaluated these models on their ability to learn from experience, adapt, and gather information.…
arXiv:2510.06028v1 Announce Type: cross Abstract: The paper provides data-dependent bounds on the test error of the Gibbs algorithm in the overparameterized interpolation regime, where low training errors are also obtained for impossible data, such as random labels in classification. The…
arXiv:2410.02086v3 Announce Type: replace-cross Abstract: A unified representation space in multi-modal learning is essential for effectively integrating diverse data sources, such as text, images, and audio, to enhance efficiency and performance across various downstream tasks. Recent binding methods, such as…
arXiv:2510.06025v1 Announce Type: cross Abstract: Out-of-Distribution (OOD) detection is critical to AI reliability and safety, yet in many practical settings, only a limited amount of training data is available. Bayesian Neural Networks (BNNs) are a promising class of model on…
arXiv:2408.06958v3 Announce Type: replace-cross Abstract: We present AuToMATo, a novel clustering algorithm based on persistent homology. While AuToMATo is not parameter-free per se, we provide default choices for its parameters that make it into an out-of-the-box clustering algorithm that performs…
arXiv:2510.05949v1 Announce Type: cross Abstract: Joint Embedding Predictive Architectures (JEPAs) learn representations able to solve numerous downstream tasks out-of-the-box. JEPAs combine two objectives: (i) a latent-space prediction term, i.e., the representation of a slightly perturbed sample must be predictable from…
arXiv:2510.05849v1 Announce Type: cross Abstract: Guiding pretrained flow-based generative models for conditional generation or to produce samples with desired target properties enables solving diverse tasks without retraining on paired data. We present ESS-Flow, a gradient-free method that leverages the typically…
