arXiv:2601.05052v1 Announce Type: cross Abstract: Building efficient and effective generative models for neural network weights has been a research focus of significant interest that faces challenges posed by the high-dimensional weight spaces of modern neural networks and their symmetries. Several prior generative models are limited to generating partial neural network weights, particularly for larger models, such as ResNet and ViT. Those that do generate complete weights struggle with generation speed or require finetuning of the generated models. In […]

Ver mais

The Middle East and Africa (MEA) region is quickly establishing itself as one of the world’s most promising frontiers for AI-led digital transformation as AI transforms economies around the world. Industry executives, legislators, and businesses convened at the Global AI Show Abu Dhabi to examine how cloud and AI technologies are transforming infrastructure, finance, governance, and innovation throughout the region. Carter Tian, Chief Solution Architect & AI Expert, representing Alibaba Cloud, gave a thorough explanation of Alibaba’s perspective […]

Ver mais

arXiv:2601.04299v1 Announce Type: new Abstract: Type 1 diabetes (T1D) is a highly metabolically heterogeneous disease that cannot be adequately characterized by conventional biomarkers such as glycated hemoglobin (HbA1c). This study proposes an explainable deep learning framework that integrates continuous glucose monitoring (CGM) data with laboratory profiles to learn multimodal temporal embeddings of individual metabolic status. Temporal dependencies across modalities are modeled using a transformer encoder, while latent metabolic phenotypes are identified via Gaussian mixture modeling. Model interpretability is […]

Ver mais

arXiv:2601.05407v1 Announce Type: new Abstract: Knowledge distillation (KD) has the potential to accelerate MARL by employing a centralized teacher for decentralized students but faces key bottlenecks. Specifically, there are (1) challenges in synthesizing high-performing teaching policies in complex domains, (2) difficulties when teachers must reason in out-of-distribution (OOD) states, and (3) mismatches between the decentralized students’ and the centralized teacher’s observation spaces. To address these limitations, we propose HINT (Hierarchical INteractive Teacher-based transfer), a novel KD framework for […]

Ver mais

arXiv:2506.13717v2 Announce Type: replace-cross Abstract: Contrastive self-supervised learning based on point-wise comparisons has been widely studied for vision tasks. In the visual cortex of the brain, neuronal responses to distinct stimulus classes are organized into geometric structures known as neural manifolds. Accurate classification of stimuli can be achieved by effectively separating these manifolds, akin to solving a packing problem. We introduce Contrastive Learning As Manifold Packing (CLAMP), a self-supervised framework that recasts representation learning as a manifold packing […]

Ver mais

Levy processes play an important role in the stochastic process theory. However, since samples are non-i.i.d., statistical learning results based on the i.i.d. scenarios cannot be utilized to study the risk bounds for Levy processes. In this paper, we present risk bounds for non-i.i.d. samples drawn from Levy processes in the PAC-learning framework. In particular, by using a concentration inequality for infinitely divisible distributions, we first prove that the function of risk error is Lipschitz continuous with a […]

Ver mais

arXiv:2601.04247v1 Announce Type: new Abstract: Existing backdoor attacks on multivariate time series (MTS) forecasting enforce strict temporal and dimensional coupling between triggers and target patterns, requiring synchronous activation at fixed positions across variables. However, realistic scenarios often demand delayed and variable-specific activation. We identify this critical unmet need and propose TDBA, a temporally decoupled backdoor attack framework for MTS forecasting. By injecting triggers that encode the expected location of the target pattern, TDBA enables the activation of the […]

Ver mais

This study introduces a pioneering digital twin platform that embeds graph neural networks (GNNs) to replicate power system topologies, where buses function as nodes and transmission lines serves as edges, facilitating precise real-time state estimation and predictive analytics. Transfer learning enables efficient adaptation of pre-trained GNN models from extensive synthetic datasets, such as modified IEEE benchmarks, to operational environments with scarce data, slashing training requirements by approximately 60% while upholding robustness across varied grid configurations from local distribution […]

Ver mais