arXiv:2601.02521v1 Announce Type: new Abstract: Automated analysis of volumetric medical imaging on edge devices is severely constrained by the high memory and computational demands of 3D Convolutional Neural Networks (CNNs). This paper develops a lightweight computer vision framework that reconciles the efficiency of 2D detection with the necessity of 3D context by reformulating volumetric Computer Tomography (CT) data as sequential video streams. This video-viewpoint paradigm is applied to the time-sensitive task of Intracranial Hemorrhage (ICH) detection using the […]

Ver mais

arXiv:2601.07876v1 Announce Type: new Abstract: This work introduces NOVAK, a modular gradient-based optimization algorithm that integrates adaptive moment estimation, rectified learning-rate scheduling, decoupled weight regularization, multiple variants of Nesterov momentum, and lookahead synchronization into a unified, performance-oriented framework. NOVAK adopts a dual-mode architecture consisting of a streamlined fast path designed for production. The optimizer employs custom CUDA kernels that deliver substantial speedups (3-5 for critical operations) while preserving numerical stability under standard stochastic-optimization assumptions. We provide fully developed […]

Ver mais

arXiv:2603.06626v1 Announce Type: new Abstract: Traditional Mixture-of-Experts (MoE) training typically proceeds without any structural priors, effectively requiring the model to simultaneously train expert weights while searching for an optimal routing policy within a vast combinatorial space. This entanglement often leads to sluggish convergence and training instabilities. This paper introduces Grouter, a preemptive routing method that by distilling high-quality structures from fully-trained MoE models and serving as a fixed router for target models. By decoupling structural optimization from weight […]

Ver mais

arXiv:2510.23935v2 Announce Type: replace Abstract: Machine learning models have achieved widespread success but often inherit and amplify historical biases, resulting in unfair outcomes. Traditional fairness methods typically impose constraints at the prediction level, without addressing underlying biases in data representations. In this work, we propose a principled framework that adjusts data representations to balance predictive utility and fairness. Using sufficient dimension reduction, we decompose the feature space into target-relevant, sensitive, and shared components, and control the fairness-utility trade-off […]

Ver mais

Introduction Creating distributed systems might need implementation of special retry mechanisms, state machines, dead letter queues, etc. Despite best practices in software design, unexpected issues may still arise in production systems, requiring manual intervention. Temporal’s approach to workflow orchestration is different from other solutions by providing durability and state management as part of the system. It has been adopted by companies such as Netflix, NVIDIA, Snap, and Airwallex in their production systems. While it is essential to understand […]

Ver mais

Apple announced the MacBook Neo two days ago. $599. iPhone chip. Four colors including “citrus” yellow. Ships March 11. I’m not an Apple user but I’ve been following rumors for a while. With the specs officially out, I have thoughts. Not all of them are positive. What it actually is MacBook Neo is the cheapest laptop Apple has ever sold. At $599 – or $499 if you’re a student – that’s great. What sucks: A18 Pro chip instead […]

Ver mais

arXiv:2601.20895v1 Announce Type: new Abstract: Research aimed at scaling up neuroscience inspired learning algorithms for neural networks is accelerating. Recently, a key research area has been the study of energy-based learning algorithms such as predictive coding, due to their versatility and mathematical grounding. However, the applicability of such methods is held back by the large computational requirements caused by their iterative nature. In this work, we address this problem by showing that the choice of initialization of the […]

Ver mais

Recent years have seen a surge in data-driven surrogates for dynamical systems that can be orders of magnitude faster than numerical solvers. However, many machine learning-based models such as neural operators exhibit spectral bias, attenuating high-frequency components that often encode small-scale structure. This limitation is particularly damaging in applications such as weather forecasting, where misrepresented high frequencies can induce long-horizon instability. To address this issue, we propose multi-scale wavelet transformers (MSWTs), which learn system dynamics in a tokenized […]

Ver mais