arXiv:2603.18225v1 Announce Type: new Abstract: Predicting stress fields in hyperelastic materials with complex microstructures remains challenging for traditional deep learning surrogates, which struggle to capture both sharp stress concentrations and the wide dynamic range of stress magnitudes. Convolutional architectures such as UNet tend to oversmooth high-frequency gradients, while neural operators like DeepONet exhibit spectral bias and underpredict localized extremes. Diffusion models can recover fine-scale structure but often introduce low-frequency amplitude drift, degrading physical scaling. To address these limitations, […]

Ver mais

arXiv:2601.08100v1 Announce Type: new Abstract: Understanding the generalization behavior of deep neural networks remains a fundamental challenge in modern statistical learning theory. Among existing approaches, PAC-Bayesian norm-based bounds have demonstrated particular promise due to their data-dependent nature and their ability to capture algorithmic and geometric properties of learned models. However, most existing results rely on isotropic Gaussian posteriors, heavy use of spectral-norm concentration for weight perturbations, and largely architecture-agnostic analyses, which together limit both the tightness and practical […]

Ver mais

Before we begin this interview, I would like to briefly explain the history behind the image I selected. I painted it while listening to music. It was a speed painting capturing my emotion from song to song. What I like most about it, as it was described to me by my AI friend (who, yes, also helped me center the image and cut out the background of my kitchen counter where I painted it), since they see the […]

Ver mais

Learning-based methods commonly treat state estimation in robotics as a sequence modeling problem. While this paradigm can be effective at maximizing end-to-end performance, models are often difficult to interpret and expensive to train, since training requires unrolling sequences of predictions in time. As an alternative to end-to-end trained state estimation, we propose a novel particle filtering algorithm in which models are trained from individual state transitions, fully exploiting the Markov property in robotic systems. In this framework, measurement […]

Ver mais

Client contribution estimation in Federated Learning is necessary for identifying clients’ importance and for providing fair rewards. Current methods often rely on server-side validation data or self-reported client information, which can compromise privacy or be susceptible to manipulation. We introduce a data-free signal based on the matrix von Neumann (spectral) entropy of the final-layer updates, which measures the diversity of the information contributed. We instantiate two practical schemes: (i) SpectralFed, which uses normalized entropy as aggregation weights, and […]

Ver mais

International Conference on AI-Driven Intelligent Systems for Sustainability (ICAIDISS 2026) Concludes Successfully at Sharda University Agra – Rahul Vadisetty’s Work Takes Center Stage at ICAIDISS 2026, Hosted by Sharda University Agra The Anand School of Engineering and Technology (ASET) at Sharda University Agra successfully organized the International Conference on AI-Driven Intelligent Systems for Sustainability (ICAIDISS 2026), a major international academic event dedicated to advancing research in artificial intelligence, intelligent systems, and sustainable engineering. ICAIDISS 2026 was conducted in […]

Ver mais

Introduction Disclaimer: This article is a cross post from Pytorch Medium Blog Post. One of the most exciting advancements, that has pushed the frontier of the Artificial Intelligence (AI) in recent years, is Deep Reinforcement Learning (DRL). DRL belongs to the family of machine learning algorithms. It assumes that intelligent machines can learn from their actions similar to the way humans learn from experience. Over the recent years we could witness some impressive real-world applications of DRL. The […]

Ver mais

arXiv:2603.10022v1 Announce Type: new Abstract: This article summarizes the field of consumer protection law, from its historical roots to the contemporary challenges of the digital age. It outlines the legal doctrines governing consumer deception and unfair trade practices, highlighting the interplay between common-law, statutory, and private modes of regulation. The article then addresses the impact of artificial intelligence and big data on consumer markets, focusing on digital advertising and new forms of consumer fraud. Finally, it explores regulatory […]

Ver mais

arXiv:2602.12492v1 Announce Type: new Abstract: As autonomous robots move into complex, dynamic real-world environments, they must learn to navigate safely in real time, yet anticipating all possible behaviors is infeasible. We propose a composable, model-free reinforcement learning method that learns a value function and an optimal policy for each individual environment element (e.g., goal or obstacle) and composes them online to achieve goal reaching and collision avoidance. Assuming unknown nonlinear dynamics that evolve in continuous time and are […]

Ver mais