arXiv:2511.03911v1 Announce Type: new Abstract: Decomposition is a proven way to shrink deep networks without changing I We bring this idea to hyperdimensional computing (HDC), where footprint cuts usually shrink the feature axis and erode concentration and robustness. Prior HDC…
arXiv:2506.15680v2 Announce Type: replace-cross Abstract: Modeling the dynamics of deformable objects is challenging due to their diverse physical properties and the difficulty of estimating states from limited visual information. We address these challenges with a neural dynamics framework that combines…
arXiv:2511.03924v1 Announce Type: new Abstract: Inferring sociodemographic attributes from mobility data could help transportation planners better leverage passively collected datasets, but this task remains difficult due to weak and inconsistent relationships between mobility patterns and sociodemographic traits, as well as…
arXiv:2511.02625v2 Announce Type: replace-cross Abstract: We present an estimation of the condition numbers of the emph{mass} and emph{stiffness} matrices arising from shallow ReLU$^k$ neural networks defined on the unit sphere~$mathbb{S}^d$. In particular, when ${theta_j^*}_{j=1}^n subset mathbb{S}^d$ is emph{antipodally quasi-uniform}, the…
arXiv:2511.03928v1 Announce Type: new Abstract: We introduce and formalize the Synthetic Dataset Quality Estimation (SynQuE) problem: ranking synthetic datasets by their expected real-world task performance using only limited unannotated real data. This addresses a critical and open challenge where data…
arXiv:2511.04550v1 Announce Type: cross Abstract: The growth of cloud computing has revolutionized data processing and storage capacities to another levels of scalability and flexibility. But in the process, it has created a huge challenge of security, especially in terms of…
arXiv:2511.03929v1 Announce Type: new Abstract: We introduce Nemotron Nano V2 VL, the latest model of the Nemotron vision-language series designed for strong real-world document understanding, long video comprehension, and reasoning tasks. Nemotron Nano V2 VL delivers significant improvements over our…
arXiv:2511.04622v1 Announce Type: cross Abstract: The Adam optimizer is currently presumably the most popular optimization method in deep learning. In this article we develop an ODE based method to study the Adam optimizer in a fast-slow scaling regime. For fixed…
arXiv:2511.03938v1 Announce Type: new Abstract: Hyperdimensional computing (HDC) suits memory, energy, and reliability-constrained systems, yet the standard “one prototype per class” design requires $O(CD)$ memory (with $C$ classes and dimensionality $D$). Prior compaction reduces $D$ (feature axis), improving storage/compute but…
arXiv:2407.03953v4 Announce Type: replace Abstract: Graph pre-training has been concentrated on graph-level tasks involving small graphs (e.g., molecular graphs) or learning node representations on a fixed graph. Extending graph pre-trained models to web-scale graphs with billions of nodes in industrial…
