Full-text search across 12457 articles. Combine with topic and date filters; results sorted by relevance.
Researchers have developed a new framework for detecting backdoor attacks in large language models, addressing the challenge of discrete input spaces. The framework introduces Class Subspace Orthogonalization (CSO) to en…
Researchers have advanced Neural Controlled Differential Equations (NCDEs) with Log-NCDEs and Linear NCDEs, reducing training time by up to three orders of magnitude while achieving state-of-the-art results on time serie…
Neural networks and logistic regression models are competing to improve stroke prediction, as strokes occur every 40 seconds in the U.S. and are a leading cause of death. Neural networks offer complex pattern recognition…
Researchers developed STST-JEPA, a self-supervised transformer model that predicts brain age from EEG data with a mean absolute error of 3.06 years, outperforming previous methods. The model, pretrained on over 47,000 se…
Researchers have developed WattCouncil, a data-generation framework that uses large language model-based agents to simulate household energy data, addressing privacy and cost barriers in smart grid research. The framewor…
Ophiuchus, a new tool-augmented framework, outperforms existing methods in medical AI diagnostics by integrating fine-grained visual evidence with multimodal reasoning. Its three-stage training approach enables precise t…
ManifoldFlow, a new approach to neural network weight constraints, introduces flexible spectral control by allowing a bounded positive spectrum instead of fixed singular values, outperforming traditional Stiefel layers i…
A new benchmarking framework for Graph Explainable AI (G-XAI) evaluates Graph Neural Networks (GNNs) using tabular explainability metrics that separate graph topology and node features, identifying non-dominated explaine…
The U.S. Army is fielding AI-enabled sensing and targeting tools including the Maven Smart System and the Tactical Intelligence Targeting Access Node (TITAN), with XVIII Airborne Corps using Maven's Broad Area Surveillan…
A reproducibility package for a machine learning-driven assessment of the equity-performance relationship in university budget allocation has been published on Zenodo with DOI 10.5281/zenodo.21149505. The package, licens…
Aggregate Asset Management's Aggregate Value Fund uses a machine learning-based stock selection engine to pick stocks, evaluating more than 150 indicators across technical analysis, company fundamentals, and academic res…
Apple released a new ad promoting Safari as a more private browsing alternative to Google Chrome, depicting Chrome's data trackers as chrome-suited figures that follow users. The ad highlights Safari's default blocking o…
A new explainer describes neural networks as machines that learn by adjusting millions of dials through repeated forward and backward passes, starting with random guesses and refining until they work. The piece, written …
Tinker's LoRA fine-tuning matches full fine-tuning performance on small datasets and reinforcement learning, but underperforms on larger supervised learning datasets, according to a technical primer from Thinking Machine…
Samruk-Energy JSC is implementing an AI and machine learning-based project to digitalize power generation planning at renewable energy facilities in Kazakhstan, with launch planned for the end of 2026. The system, which …
AI integration in security systems requires human oversight to ensure accountability and adaptability, as shared architectures create blind spots and systemic errors. A balanced division of labor between AI and humans is…
The PnPBO framework, a plug-and-play architecture for bilevel optimization, achieves optimal sample complexity comparable to single-level optimization by integrating modern unbiased and biased stochastic estimators. Rese…
Researchers Samip Dahal, Bishwas Mandal, Serdar Gülbahar and Akshay Vegesna released Dust, a zeroth-order pretraining method that perturbs activations independently at every token so one forward pass evaluates a virtual …
A National Bureau of Economic Research working paper analyzing 29.4 million U.S. LinkedIn profiles finds that 19.7% of established users retroactively edited a past job title or description between 2020 and 2026, with AI…
Archal.AI, a Y Combinator S26 startup, launched an evaluation platform that provides deterministic, stateful clones of third-party SaaS services for testing AI agents without affecting live systems. Founded in 2026 by No…