Abstract Artificial intelligence (AI) is increasingly being incorporated into coding and programming education through conversational tutors, automated feedback systems, adaptive scaffolding, multimodal learning environments, and AI-assisted programming tools. While these technologies can provide immediate assistance a...
Janix Asare· Zenodo (CERN European Organi...· 0 citations
Vision-language models are a form of multimodal AI that encode language and visual information jointly for a range of downstream tasks, however interpretation of how they understand the input across modalities remains difficult. This work uses Sparse Autoencoders (SAEs) to interpret a self-supervised audio-visual model...
Brian Diep· cIRcle (University of Britis...· 0 citations
Small VCF databases, one per cohort. Variants, genotypes, and samples live in either chDB (embedded ClickHouse) or DuckDB; gene and ClinVar annotations live in a sibling DuckDB file. A bundled Model Context Protocol server exposes a small set of tools so a language-model client can query the cohort in natural language...
Paulo A. F. Nuin· Zenodo (CERN European Organi...· 0 citations
As a continuation of our previous work, we publish the paper resolving the open Automata Exchange Problem 24.04(A) by showing that the problem is decidable. Unlike Problem 24.04(B), Problem 24.04(A) was not stated precisely enough to make clear whether epsilon-moves were included in the model. For this reason, we solve...
Alp Eren Bütün· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
As a continuation of our previous work, we publish the paper resolving the open Automata Exchange Problem 24.04(A) by showing that the problem is decidable. Unlike Problem 24.04(B), Problem 24.04(A) was not stated precisely enough to make clear whether epsilon-moves were included in the model. For this reason, we solve...
Alp Eren Bütün· Zenodo (CERN European Organi...· 0 citations
This is a major release. The most important feature is that local LLM models can now be used (and are automatically installed when required). This allows you to experiment with Plainbook locally and at no cost, in case you don't have an API key. Of course, the local model is not as good as cloud models, but it can stil...
Luca de Alfaro, Mathis Aubert, Ranjit Jhala et al.· Zenodo (CERN European Organi...· 0 citations
This is a major release. The most important feature is that local LLM models can now be used (and are automatically installed when required). This allows you to experiment with Plainbook locally and at no cost, in case you don't have an API key. Of course, the local model is not as good as cloud models, but it can stil...
Luca de Alfaro, Mathis Aubert, Ranjit Jhala et al.· Zenodo (CERN European Organi...· 0 citations
Cardiovascular diseases (CVDs) are a public health issue in many countries and the primary cause of disease burden worldwide, leading to the increasing cost of health care. Artificial intelligence (AI) and machine learning (ML) tools offer promising solutions for predicting health care costs for cardiovascular pa...
Alireza Banaye Yazdipour, Mohammad Amiri-Ara, Parisa Mehdizadeh· BMC Medical Informatics and...· 0 citations
BACKGROUND
Frequent callers and users of ambulance services represent a small but complex patient cohort who account for a disproportionate number of emergency medical service contacts. Although frequent use has been examined in emergency department settings, less is known about frequent use in the out-of-hospital ambu...
RATIONALE
Loss of skeletal muscle mass and function is a common, debilitating complication of kidney failure for individuals undergoing dialysis. It contributes to reduced physical capacity, quality of life (QoL), and increased death. Exercise training can mitigate these effects, but participation is often limited by c...
L. Beresford, Louise C. Burgess, Susan Dewhurst et al.· Cochrane Database of Systema...· 0 citations
This project investigates the use of self-hosted Large Language Models (LLMs) for processing Polish medical text within a GDPR-compliant, on-prem environment. The goal is to assess whether relatively small, locally deployed LLMs can be used in tasks such as data extraction and translation of Polish medical records. We...
Filip Katulski, Paulina Tworek, Andrzej Chrobot et al.· Proceedings of the Internati...· 0 citations
Peri-implantitis is a biofilm-induced, immune-mediated inflammatory condition affecting ~1 in 5 patients bearing implants and remains one of the most clinically unresolved challenges in contemporary implantology.Although multiple therapeutic approaches have been proposed, no universally accepted treatment protocol exis...
Richik Chakraborty, Nina Shenoy, Avaneendra Talwar et al.· World Academy of Sciences Jo...· 0 citations
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
