Category
3,683 papers
Neural networks often learn low-frequency components before high-frequency ones --- a phenomenon called spectral bias or termed F-principle. Many numerical studies have demonstrated this phenomenon, and theoretical studies have sought to explain it. However, several goals remain insufficiently addressed: (1) explaining...
Sequence models can generalise in fundamentally distinct ways: extrapolating structures seen in training, or using their prompt to adapt to novel tasks. The prevailing strategy determines how the model behaves beyond its training distribution, controlling potential capabilities and risks. Recent work has characterised...
Risk-sensitive reinforcement learning (RL) addresses decision-making under uncertainty and adverse outcomes. Learning risk-sensitive policies from fixed datasets is important when additional interaction with the environment is costly. Existing work on risk-sensitive RL focuses on online settings or specific risk measur...
Muon replaces a matrix gradient by an approximate polar factor and has shown strong empirical performance in neural-network training. The Isotropic Curvature Model (ICM) provides a curvature-based explanation for this update by asking when gradient orthogonalization minimizes a one-step local-loss surrogate. We investi...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Feedback noise is pervasive in preference data, arising from subjective human judgments, annotation mistakes, and imperfect LLM judges. Standard reward modeling trained on such feedback yields a biased estimate of the clean risk. Although classical denoising methods are directly applicable to noisy feedback learning, t...
When every rollout for a problem fails, GRPO receives neither a successful exemplar nor a nonzero group-relative advantage, so it learns nothing from exactly the problems it most needs to learn. The failed reasoning can nevertheless suggest what to try next. We present Replay-Selected Hindsight Distillation (RSHD), whi...
A scientific-based approach based on data-driven decision making and empirical studies is an essential characteristic of today’s applied science and technology subjects. This empirical research aims to investigate the current status of statistical awareness, literacy and the software application skill of the undergradu...
As artificial intelligence reshapes virtually every field, universities face a growing imperative to ensure AI literacy is not reserved for computer science majors alone. This panel presents the collaborative design of an introductory AI course built for undergraduate general education — one that serves students across...
Abstract The Jiangmen Underground Neutrino Observatory (JUNO) is a 20-kiloton liquid scintillator neutrino detector, located 650 meters (1800 m.w.e.) underground in Jiangmen, Guangdong, China. JUNO is primarily designed for reactor neutrino measurements and has been taking data since 2025. With the largest mass of its...
Heart failure (HF) is a chronic syndrome requiring treatment, symptom monitoring, and coordinated care. Self-care includes health maintenance, recognition of changes, and responses, but may be affected by treatment complexity, comorbidities, health literacy, social support, and access to care. Smartphones offer tools s...
International research collaboration (IRC) is now a central feature of higher education systems and is increasingly used as evidence of institutional quality, research excellence, and internationalisation. IRC is usually evaluated through co-authorships, especially international co-authored publications identified thro...
This study investigates the research landscape with respect to virtual assets that are involved in financial crime, with a focus on terrorism financing and money laundering. This study employs a bibliometric analysis of 796 peer-reviewed articles retrieved from the Scopus Database (2000–2024). Bibliometrics...
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Health & Bioscience
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Data Mining & Modeling
GPT-Lab
· gpt-lab.eu
Nov 3, 2026
Is your company’s AI sovereign? A practical guide for CIOs on AI vendor lock-in, EU Data Act switching, cloud sovereignty, and testing your exit plan before you need it. The post Sovereignty Is the Option to Leave appeared first on GPT-Lab.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
