Stay updated with the latest research and technology news
arXiv:2506.01582v3 Announce Type: replace-cross Abstract: We introduce the attention-indexed model (AIM), a theoretical framework for analyzing learning in deep attention layers. Inspired by multi-index models,...
arXiv:2506.17093v3 Announce Type: replace-cross Abstract: Polynomial Neural Networks (PNNs) possess a rich algebraic and geometric structure. However, their identifiability -- a key property for ensuring...
arXiv:2507.03245v3 Announce Type: replace-cross Abstract: Parametric data-driven reduced-order models (ROMs) that embed dependencies in a large number of input parameters are crucial for enabling many-query...
arXiv:2507.04603v2 Announce Type: replace-cross Abstract: We study the one-dimensional capillary-driven retraction of a finite, planar liquid sheet in the asymptotic regime where both the Ohnesorge...
arXiv:2507.18220v2 Announce Type: replace-cross Abstract: The sparse identification of nonlinear dynamics (SINDy) approach can discover the governing equations of dynamical systems based on measurement data,...
arXiv:2508.10992v2 Announce Type: replace-cross Abstract: Synchronization is a fundamental phenomenon in complex systems, observed across a wide range of natural and engineered contexts. The Kuramoto...
arXiv:2508.20713v4 Announce Type: replace-cross Abstract: We prove that for translationally invariant quantum spin chains with finite-range interactions, the existence of a specific conservation law known...
arXiv:2509.00686v5 Announce Type: replace-cross Abstract: We discuss scalar field theories with potentials V({\phi})=\k{appa}({\phi}^2)^{{\nu}} for generic {\nu}. We conjecture that these models evade various no-go theorems...
arXiv:2509.23162v2 Announce Type: replace-cross Abstract: Dense associative memories (DAMs) store and retrieve patterns via energy-function based fixed points, but existing models are limited to vector...
arXiv:2509.23199v2 Announce Type: replace-cross Abstract: We describe the blowup scenarios in a phase-parametrized differential approximation kinetic model (N-DAM), inspired by the physics of deep water...
arXiv:2509.24914v2 Announce Type: replace-cross Abstract: Trained attention layers exhibit striking and reproducible spectral structure of the weights, including low-rank collapse, bulk deformation, and isolated spectral...
arXiv:2510.01464v2 Announce Type: replace-cross Abstract: Onion routing provides anonymity by layering encryption so that no relay can link sender to destination. A quantum analogue faces...
arXiv:2510.02174v2 Announce Type: replace-cross Abstract: Flatness of the loss landscape has been widely studied as an important perspective for understanding the behavior and generalization of...
arXiv:2510.08582v4 Announce Type: replace-cross Abstract: This paper introduces a modular and scalable design optimization framework for the wing design process that enables faster early-phase design...
arXiv:2511.01079v2 Announce Type: replace-cross Abstract: Neural image compression (NIC) has become the state-of-the-art for rate-distortion performance, yet its security vulnerabilities remain significantly less understood than...
arXiv:2511.06189v2 Announce Type: replace-cross Abstract: We address the challenge of forecasting counterfactual outcomes in a panel data with missing entries and temporally dependent latent factors...
arXiv:2511.12384v2 Announce Type: replace-cross Abstract: In the day-ahead energy market, the offering strategy of distributed energy resource (DER) aggregators must be submitted before the uncertainty...
arXiv:2511.21595v2 Announce Type: replace-cross Abstract: The effective degrees of freedom of penalized regression models quantify the actual amount of information used to generate predictions, playing...
arXiv:2512.06494v3 Announce Type: replace-cross Abstract: This letter describes how to improve performance of cellular systems by combining non-equiprobable signaling (shaping) with low-density parity check (LDPC)...
arXiv:2512.20576v2 Announce Type: replace-cross Abstract: Post-deployment machine learning algorithms often influence the environments they act in, and thus shift the underlying dynamics that the standard...
arXiv:2512.21208v2 Announce Type: replace-cross Abstract: We propose a unified analytic and variational framework for stability in deep learning systems viewed as coupled representation-parameter dynamics. The...
arXiv:2512.22863v2 Announce Type: replace-cross Abstract: This paper presents a counterexample to the optimality conjecture in convex quantum channel optimization proposed by Coutts et al. The...
arXiv:2512.22997v2 Announce Type: replace-cross Abstract: We introduce generalisations of von Neumann entanglement entropy that are invariant with respect to certain scale transformations. These constructions are...
arXiv:2601.05954v2 Announce Type: replace-cross Abstract: In 1+1-dimensions, an extension of the canonical solitonic Dym equation has previously been derived both in a geometric torsion evolution...