arXiv:2511.21934v1 Announce Type: new Abstract: Feature transformation enhances downstream task performance by generating informative features through mathematical feature crossing. Despite the advancements in deep learning, feature transformation remains essential for structured data, where deep models often struggle to capture complex…
arXiv:2511.13053v5 Announce Type: replace Abstract: Kernel-based learning methods can dramatically increase the storage capacity of Hopfield networks, yet the dynamical mechanism behind this enhancement remains poorly understood. We address this gap by unifying the geometric analysis of the attractor landscape…
arXiv:2511.21935v1 Announce Type: new Abstract: AI agents are increasingly deployed in ecosystems where they repeatedly interact not only with each other but also with humans. In this work, we study these human-AI ecosystems from a theoretical perspective, focusing on the…
arXiv:2309.16858v3 Announce Type: replace-cross Abstract: We introduce Transductive Local Complexity (TLC) as a new tool for analyzing the generalization performance of transductive learning methods. Our work extends the classical Local Rademacher Complexity (LRC) to the transductive setting, incorporating substantial and…
arXiv:2511.21940v1 Announce Type: new Abstract: Non-invasive Brain-Computer Interfaces (BCIs) based on Code-Modulated Visual Evoked Potentials (C-VEPs) require highly robust decoding methods to address temporal variability and session-dependent noise in EEG signals. This study proposes and evaluates several deep learning architectures,…
arXiv:2503.08921v2 Announce Type: replace-cross Abstract: We introduce a new projection-free (Frank-Wolfe) method for optimizing structured nonconvex functions that are expressed as a difference of two convex functions. This problem class subsumes smooth nonconvex minimization, positioning our method as a promising…
arXiv:2511.21952v1 Announce Type: new Abstract: Machine learning models are increasingly used in critical applications but are mostly “black boxes” due to their lack of transparency. Local explanation approaches, such as LIME, address this issue by approximating the behavior of complex…
arXiv:2507.06764v3 Announce Type: replace-cross Abstract: In this work, we propose Fast Equivariant Imaging (FEI), a novel unsupervised learning framework to rapidly and efficiently train deep imaging networks without ground-truth data. From the perspective of reformulating the Equivariant Imaging based optimization…
arXiv:2511.21963v1 Announce Type: new Abstract: Click-through rates prediction is critical in modern advertising systems, where ranking relevance and user engagement directly impact platform efficiency and business value. In this project, we explore how to model CTR more effectively using a…
arXiv:2510.20406v2 Announce Type: replace-cross Abstract: Robotic manipulation systems benefit from complementary sensing modalities, where each provides unique environmental information. Point clouds capture detailed geometric structure, while RGB images provide rich semantic context. Current point cloud methods struggle to capture fine-grained…
