Category
3,683 papers
Gaussian diffusion models offer a practical framework for generative modeling. Denoising L\'{e}vy Probabilistic Models (DLPM) introduce heavy-tailed perturbations with a fixed tail index throughout denoising. We introduce Annealed L\'{e}vy Diffusion (ALD). ALD varies the stability index $\alpha(t)$ to combine heavy-tai...
Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in language models, but scalar outcomes provide coarse supervision over response trajectories. Self-distillation offers denser token-level guidance by comparing an unassisted policy with a feedback-informed self-teacher, yet the teacher evolves wi...
Recent work has sought to transfer first-order nonconvex optimization guarantees to zeroth-order methods through gradient estimators, typically incurring a factor linear in $d$. \citet{kornowski2024} obtained an $\mathcal{O}(d\delta^{-1}\epsilon^{-3})$ oracle complexity for nonsmooth nonconvex optimization and asked wh...
Information-theoretic exploration is of primary interest in methodological studies of reinforcement learning (RL) and computational cognitive neuroscience, while the established RL theory builds regret guarantees on confidence sets. This situation leaves open the conditions under which the information-driven exploratio...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Understanding the mechanism behind why diffusion models memorize their training data remains an open question in generative modeling. In this paper, we examine this question from two perspectives: (a) the model-level perspective concerning the onset of memorization in a model during training, and (b) the sample-level p...
Post-training reasoning LLMs often requires making a tradeoff between costly supervision and compute inefficiency: supervised finetuning typically requires reasoning traces, which is data inefficient since in many applications one only has prompt-answer tuples and lacks the groundtruth chain-of-thought (CoT) sequence....
Context: Several countries have endorsed the United Nations agencies' mandate on inclusive vocational education and training (VET) for learners with special educational needs (SEN). Despite these robust international commitments, empirical evidence supporting inclusive VET remains dispersed across disciplines, national...
Using a proprietary data set that documents corporate bond issuances in China, we find that bond regulators’ comment letters (CLs) on issuers’ public disclosures generally target opaque firms and reduce bond issuance success. We also find, however, that connected investors—financial institutions with prior business rel...
Maternal Near Miss (MNM) serves as a critical indicator for evaluating the quality of obstetric care. This study aimed to analyze the trends, primary causes, and socio-demographic determinants of MNM cases over a five-year period across the affiliated hospital network of Mashhad University of Medical Sciences in Northe...
This record contains the analysis scripts and derived data for the manuscript "Which timing matters? Hazard-specific drivers of tropical-cyclone landslides and floods in Hong Kong, 1986–2024", submitted to Natural Hazards and Earth System Sciences. The study examines 61 tropical cyclones that passed within 200 km of Ho...
Exercise and sport sciences increasingly rely on statistical models to analyse complex data arising from experimental, observational, and longitudinal designs. However, applied research frequently shows misalignment between research questions, data structure, and analytical strategies, leading to biased inference, limi...
Infectious diseases significantly contribute to mortality and pose a growing public health challenge. Early diagnosis and treatment of acute bacterial infections are critical but often hindered by delayed or inadequate treatment. Rapid and accurate diagnostic tools are essential to manage such infections effectively. D...
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.
