arXiv:2603.06611v1 Announce Type: new Abstract: Fecal-contaminated water causes diseases and even death. Current microbial water safety tests require pathogen incubation, taking 24-72 hours and costing $20-$50 per test. This paper presents a solution (DeepScope) exceeding UNICEF’s ideal Target Product Profile requirements for presence/absence testing, with an estimated per-test cost of $0.44. By eliminating the need for pathogen incubation, DeepScope reduces testing time by over 98%. In DeepScope, a dataset of microscope images of bacteria and water samples was […]

Ver mais

We study supervisory switching control for partially-observed linear dynamical systems. The objective is to identify and deploy the best controller for the unknown system by periodically selecting among a collection of $N$ candidate controllers, some of which may destabilize the underlying system. While classical estimator-based supervisory control guarantees asymptotic stability, it lacks quantitative finite-time performance bounds. Conversely, current non-asymptotic methods in both online learning and system identification require restrictive assumptions that are incompatible in a control setting, such […]

Ver mais

Welcome to the third edition of HackerNoon Projects of the Week, where we spotlight standout projects from the Proof of Usefulness Hackathon, HackerNoon’s competition designed to measure what actually matters: real utility over hype. n n Each week, we’ll highlight projects that demonstrate clear usefulness, technical execution, and real-world impact – backed by data, not buzzwords. This week, we’re excited to share three projects that have proven their utility by solving concrete problems for real users: QuantumLayer, Ekstra AI, […]

Ver mais

Self-supervised pre-training with contrastive learning is a powerful method for learning from sparsely labeled data. However, performance can drop considerably when there is a shift in the distribution of data from training to test time. We study this phenomenon in a setting in which the training data come from multiple domains, and the test data come from a domain not seen at training that is subject to significant covariate shift. We present a new method for contrastive learning […]

Ver mais

I am putting all the new code and documentation about xLLM v 2.0 on GitHub, starting with various AI agents. At least, what is open-source and public (there is a lot more behind the public material). All home-made from scratch with radically different technology. You can check the new repository, here. Start with the README file at the top of the repository, here. No Blackbox, no external API calls, and minimum reliance on Python libraries such as TensorFlow, […]

Ver mais

arXiv:2604.07396v1 Announce Type: new Abstract: Large Language Model (LLM) inference on edge Neural Processing Units (NPUs) is fundamentally constrained by limited on-chip memory capacity. Although high-density embedded DRAM (eDRAM) is attractive for storing activation workspaces, its periodic refresh consumes substantial energy. Prior work has primarily focused on reducing off-chip traffic or optimizing refresh for persistent Key-Value (KV) caches, while transient and error-resilient Query and Attention Output (QO) activations are largely overlooked. We propose SHIELD, a lifecycle-aware segmented eDRAM […]

Ver mais

arXiv:2604.06701v1 Announce Type: cross Abstract: Autoencoders are widely used for dimensionality reduction, based on the assumption that high-dimensional data lies on low-dimensional manifolds. Regularized autoencoders aim to preserve manifold geometry during dimensionality reduction, but existing approaches often suffer from non-injective mappings and overly rigid constraints that limit their effectiveness and robustness. In this work, we identify encoder non-injectivity as a core bottleneck that leads to poor convergence and distorted latent representations. To ensure robustness across data distributions, we […]

Ver mais

Claude can code, but can it check binary executables? We already did our experiments with using NSA software to hack a classic Atari game. This time, we want to focus on a much more practical task — using AI agents for malware detection. We partnered with Michał “Redford” Kowalczyk,a reverse engineering expert from Dragon Sector, known for finding malicious code in Polish trains, to create a benchmark of finding backdoors in binary executables, without access to source code. […]

Ver mais

Active learning for photonic crystals explores the integration of analytic approximate Bayesian last layer neural networks (LL-BNNs) with uncertainty-driven sample selection to accelerate photonic band gap prediction. We employ an analytic LL-BNN formulation, corresponding to the infinite Monte Carlo sample limit, to obtain uncertainty estimates that are strongly correlated with the true predictive error on unlabeled candidate structures. These uncertainty scores drive an active learning strategy that prioritizes the most informative simulations during training. Applied to the task […]

Ver mais

Great news—we’ve hit our (very modest) performance goals for the CPython JIT over a year early for macOS AArch64, and a few months early for x86_64 Linux. The 3.15 alpha JIT is about 11-12% faster on macOS AArch64 than the tail calling interpreter, and 5-6%faster than the standard interpreter on x86_64 Linux. — Ken Jin, Python 3.15’s JIT is now back on track Tags: python

Ver mais