arXiv:2512.17970v1 Announce Type: new Abstract: Weight-only quantization is widely used to mitigate the memory-bound nature of LLM inference. Codebook-based methods extend this trend by achieving strong accuracy in the extremely low-bit regime (e.g., 2-bit). However, current kernels rely on dequantization,…
arXiv:2512.17969v1 Announce Type: new Abstract: Convolutional neural operator is a CNN-based architecture recently proposed to enforce structure-preserving continuous-discrete equivalence and enable the genuine, alias-free learning of solution operators of PDEs. This neural operator was demonstrated to outperform for certain cases…
arXiv:2506.09574v2 Announce Type: replace Abstract: Sample efficiency and exploration remain critical challenges in Deep Reinforcement Learning (DRL), particularly in complex domains. Offline RL, which enables agents to learn optimal policies from static, pre-collected datasets, has emerged as a promising alternative.…
arXiv:2512.18035v1 Announce Type: new Abstract: The rapid advancements in artificial intelligence (AI) have primarily focused on the process of learning from data to acquire knowledgeable learning systems. As these systems are increasingly deployed in critical areas, ensuring their privacy and…
arXiv:2509.21605v2 Announce Type: replace Abstract: Operator learning is a recently developed generalization of regression to mappings between functions. It promises to drastically reduce expensive numerical integration of PDEs to fast evaluations of mappings between functional states of a system, i.e.,…
arXiv:2512.18056v1 Announce Type: new Abstract: Understanding user identity and behavior is central to applications such as personalization, recommendation, and decision support. Most existing approaches rely on deterministic embeddings or black-box predictive models, offering limited uncertainty quantification and little insight into…
arXiv:2512.10427v3 Announce Type: replace Abstract: Neural scaling laws and double-descent phenomena suggest that deep-network training obeys a simple macroscopic structure despite highly nonlinear optimization dynamics. We derive such structure directly from gradient descent in function space. For mean-squared error loss,…
arXiv:2512.18104v1 Announce Type: new Abstract: Aleatoric uncertainties – irremovable variability in microstructure morphology, constituent behavior, and processing conditions – pose a major challenge to developing uncertainty-robust digital twins. We introduce the Variational Deep Material Network (VDMN), a physics-informed surrogate model…
arXiv:2504.01570v2 Announce Type: replace-cross Abstract: With the aim of generalizing histogram statistics to higher dimensional cases, density estimation via discrepancy based sequential partition (DSP) has been proposed to learn an adaptive piecewise constant approximation defined on a binary sequential partition…
arXiv:2512.18120v1 Announce Type: new Abstract: Inverse problems challenge existing neural operator architectures because ill-posed inverse maps violate continuity, uniqueness, and stability assumptions. We introduce B2B${}^{-1}$, an inverse basis-to-basis neural operator framework that addresses this limitation. Our key innovation is to…
