Objectives To compare the effect of combined physical training (PT) and cognitive training (CT) with single-modality interventions, on depression symptoms in adults across clinical populations. Methods PubMed, Scopus, Web of Science, SPORTDiscus, and APA PsycINFO were systematically searched for relevant English-langua...
Piesie A. G. Asuako, Ghazal Naser, Luis K H Holzhauer et al.· Frontiers in Psychology· 0 citations
The article proposes the Human-Supervised Generative AI Framework for Physical Education and Sport, which classifies tasks by consequence and requires source grounding, data minimization, professional review, disclosure, and outcome monitoring.
NepEduBench, an initial benchmark foropen-source Small Language Models (SLMs) covering English, Nepali, and Romanized Nepali. Built from Nepal’s official Grade 6–10 Social Studies textbooks, it combines a parallel core of 318 lessons per language (the same lessons in all three languages), language-specific instruction...
Inisha Pradhan, Chutiporn Anutariya, SEIN MINN et al.· Zenodo (CERN European Organi...· 0 citations
(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Two literatures make claims about what happens when a language model trains on data that resembles its own distribution. One asks whether reinforcement learning forgets a model's prior capabilities less than supervised fine-tuning does, and answers yes: on-policy R...
Pranay M. Mahendrakar· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Two literatures make claims about what happens when a language model trains on data that resembles its own distribution. One asks whether reinforcement learning forgets a model's prior capabilities less than supervised fine-tuning does, and answers yes: on-policy R...
Pranay M. Mahendrakar· Zenodo (CERN European Organi...· 0 citations
Prefix adders are fundamental arithmetic circuits, but their design space grows exponentially with bit-width, posing significant optimization challenges. Previous works face limitations in performance, generalization, and scalability. To address these challenges, we propose PrefixAgent , a large language model (LLM)-po...
Dongsheng Zuo, Jiadong Zhu, Yang Luo et al.· ACM Transactions on Design A...· 0 citations
Background Healthy lifestyle management is essential for chronic disease prevention and long-term care. However, evidence linking lifestyle behaviors, biological mechanisms, and health outcomes is dispersed across diverse biomedical sources. This fragmentation makes it difficult for health professionals to efficiently...
Hong-Yu Kang, Xiao-Wei Xu, Ning Xiao et al.· Frontiers in Public Health· 0 citations
Almost every language model in service was trained by one family of software. That concentration makes a question hard to settle: how much of what is known about training a language model describes language models, and how much describes that software? Settling it needs a second implementation able to carry a model thr...
HistoRAG is presented, a question answering assistant that answers from one regional collection and cites a volume and a page for every fact, at a far smaller cost per question than a graph based retrieval system.
A modular, predictor agnostic, tool-augmented framework that equips a small VLM with geometric tools: 3D object detection, metric depth estimation, and deterministic solvers for distance, size and bearing, matching a scripted pipeline on three of four tasks.
Public software repositories, like GitHub and Software Heritage Archive, store billions of files, yet extracting their implicit engineering knowledge ---i.e., the algorithms they implement, the paradigms they follow, the patterns they instantiate, and the application domains they serve--- remains challenging, as curren...
Federico Pennino, Andrea Gurioli, Stefano Zacchiroli et al.· 0 citations
Results show that BLV-focused post-training improves both accessibility-specific spatial grounding and general visual-text reasoning, and is substantially outperforms the baseline across various benchmarks.
Rishabh C. Choudhary, S. Raj, Umesh Goyal et al.· 0 citations
