arXiv:2511.09763v1 Announce Type: new Abstract: We consider the relative abilities and limitations of computationally efficient algorithms for learning in the presence of noise, under two well-studied and challenging adversarial noise models for learning Boolean functions: malicious noise, in which an…
arXiv:2505.13813v2 Announce Type: replace Abstract: The Kolmogorov-Arnold Network (KAN) has been gaining popularity as an alternative to the multi-layer perceptron (MLP) with its increased expressiveness and interpretability. Even so, the KAN suffers from being orders of magnitude slower due to…
arXiv:2501.05457v2 Announce Type: replace-cross Abstract: “How to evaluate the de novo designs proposed by a generative model?” Despite the transformative potential of generative deep learning in drug discovery, this seemingly simple question has no clear answer. The absence of standardized…
arXiv:2507.03732v2 Announce Type: replace-cross Abstract: Fine, regular, and star triangulations (FRSTs) of four-dimensional reflexive polytopes give rise to toric varieties, within which generic anticanonical hypersurfaces yield smooth Calabi-Yau threefolds. We introduce CYTransformer, a deep learning model based on the transformer…
arXiv:2508.03210v2 Announce Type: replace Abstract: We provide new convergence guarantees in Wasserstein distance for diffusion-based generative models, covering both stochastic (DDPM-like) and deterministic (DDIM-like) sampling methods. We introduce a simple framework to analyze discretization, initialization, and score estimation errors. Notably,…
arXiv:2511.07170v2 Announce Type: replace Abstract: Current graph neural network (GNN) model-stealing methods rely heavily on queries to the victim model, assuming no hard query limits. However, in reality, the number of allowed queries can be severely limited. In this paper,…
arXiv:2301.12778v4 Announce Type: replace Abstract: We report the findings of a reimplementation of 18 foundational studies in feature-based machine learning for Android malware detection, published during the period 2013-2023. These studies are reevaluated on a level playing field using a…
arXiv:2503.19333v2 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) have demonstrated promise as a framework for solving forward and inverse problems involving partial differential equations. Despite recent progress in the field, it remains challenging to quantify uncertainty in these networks.…
arXiv:2511.09596v1 Announce Type: new Abstract: The design of Large Language Models (LLMs) has long been hampered by a fundamental conflict within their core attention mechanism: its remarkable expressivity is built upon a computational complexity of $O(H cdot N^2)$ that grows…
arXiv:2511.10440v1 Announce Type: cross Abstract: Protein structure determination has long been one of the primary challenges of structural biology, to which deep machine learning (ML)-based approaches have increasingly been applied. However, these ML models generally do not incorporate the experimental…
