Articles by Simon Valentin
Inspectable tabular foundation models via in-context kernel learning
Tabular foundation models like TabPFN and TabICL achieve state-of-the-art performance through in-context learning, yet their architectures remain fundamentally opaque. We introduce KernelICL, a framework to enhance tabular foundation models with quantifiable sample-based inspectability.
ICML 2026
Expo Talk: Strands robots: Unifying robot control, simulation, and training behind natural language July 7, 12:00 AM - 1:00 AM KST Room: Hall B2 Speakers: Cagatay Cali, Yin Song Abstract: Despite rapid advances in vision-language-action (VLA) models, deploying robot intelligence remains fragmented: different SDKs for different robots, different policy frameworks with incompatible interfaces, an unbridged simulation-to-reality gap, and training pipelines that demand specialist expertise .
Cost-effective hallucination detection for LLMs
Large language models (LLMs) can be prone to hallucinations —generating unreliable outputs that are unfaithful to their inputs, external facts or internally inconsistent. In this work, we address several challenges for post-hoc hallucination detection in production settings.
Altered Static Respiratory Compliance Under Invasive Mechanical Ventilation in SARS-CoV-2 infection in the Development of Respiratory Sequelae
Keywords COVID-19 respiratory insufficiency ventilator-induced lung injury respiratory distress syndrome Abbreviations ARDS (Acute Respiratory Distress Syndrome) BMI (Body Mass Index) CARDS (COVID-19 associated ARDS) CI (Confidence Intervals) COVID-19 (Coronavirus disease 2019) CRS (Static respiratory compliance) CT (Computerized Tomography) FiO2 (Inhaled fraction of oxygen) FVC (Forced Vital Capacity) GLI (Global Lung Function Initiative) ICU (Intensive Care Unit) LLN (Lower Limit of Normal)...
Simón Carlo Valentín of MZLS joins IRG as a member in Puerto Rico
IR Global, the world’s largest exclusive network of advisory firms is delighted to introduce Simón Carlo Valentín, Esq., CPA as our exclusive Tax (Law) member in Puerto Rico. Simón Carlo is a dynamic executive and skilled professional with a strong focus on the intersection of law and taxes.
Reduced symptoms of anxiety among professional caregivers facing cardiac arrest after simulation based training - Scientific Reports
Abstract Professional caregivers often suffer from post-traumatic stress disorder after intra-hospital cardiac arrest. The aim of our study was to describe long-term evolution of symptoms of anxiety among professional caregivers after a simulation-based training. Our study was a prospective, single-center pilot study conducted at Nancy-Brabois University Hospital.
Long‐term follow‐up of neutrophil activation after severe‐to‐critical SARS‐CoV‐2 infection: A longitudinal study
DATA AVAILABILITY STATEMENT The data that support the findings of this study are available from the corresponding author upon reasonable request.
Designing optimal behavioral experiments using machine learning
Introduction Computational modeling of behavioral phenomena is currently experiencing rapid growth, in particular with respect to methodological improvements. For instance, seminal work by Wilson and Collins, 2019 has been crucial in raising methodological standards and bringing attention to how computational analyses can add value to the study of human (and animal) behavior.
Probabilistic demand forecasting with graph neural networks
Demand forecasting is a prominent business use case that allows retailers to optimize inventory planning, logistics, and core business decisions. One of the key challenges in demand forecasting is accounting for relationships and interactions between articles. Most modern forecasting approaches provide independent article-level predictions that do not consider the impact of related articles.
Respiratory recovery trajectories after severe-to-critical COVID-19: a 1-year prospective multicentre study
Introduction Since its onset in January 2020, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic has been responsible for more than 600 million cases worldwide, with at least 6.6 million deaths attributed to coronavirus disease 2019 (COVID-19).
Respiratory recovery trajectories after severe-to-critical COVID-19: a 1-year prospective multicentre study
Respiratory function trajectories and HR-QoL DLCO (% pred.), FVC (% pred.), SF-36-assessed PCS- and MCS-score evolutions, according to follow-up duration (until M3, M6 or M12) are illustrated in figure 2. The mean DLCO and FVC gains (% pred.), respectively were +4.1 and +4.3 points at M6, and +6.5 and +5.9 points at M12 (for each, p<0.001; table 4).
Outcomes of patients with decreased arterial oxyhaemoglobin saturation on pulmonary arterial hypertension drugs
Simon Valentin, Arnaud Maurac, Olivier Sitbon, Antoine Beurnier, Emmanuel Gomez, Anne Guillaumot, Laura Textoris, Renaud Fay, Laurent Savale, Xavier Jaïs, David Montani, François Picard, Jean-François Mornex, Grégoire Prevot, François Chabot, Marc Humbert, Ari Chaouat European Respiratory Journal 2021 58: 2004066; DOI: 10.1183/13993003.04066-2020 Abstract Background Drugs approved for the treatment of pulmonary arterial hypertension (PAH) improve long-term outcomes.
Outcomes of patients with decreased arterial oxyhaemoglobin saturation on pulmonary arterial hypertension drugs
Simon Valentin, Arnaud Maurac, Olivier Sitbon, Antoine Beurnier, Emmanuel Gomez, Anne Guillaumot, Laura Textoris, Renaud Fay, Laurent Savale, Xavier Jaïs, David Montani, François Picard, Jean-François Mornex, Grégoire Prevot, François Chabot, Marc Humbert, Ari Chaouat European Respiratory Journal 2021; DOI: 10.1183/13993003.04066-2020 Abstract Rationale Drugs approved for the treatment of pulmonary arterial hypertension (PAH) improve long-term outcomes.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Simon
Contact Simon, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack