output
20172026
most citedMedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation

173 citations

12 papers

cs.CY2026

What if AI systems weren't chatbots?

Sourojit Ghosh, Pranav Narayanan Venkit, Sanjana Gautam +1

The rapid convergence of artificial intelligence (AI) toward conversational chatbot interfaces marks a critical moment for the industry. This paper argues that the chatbot paradigm…

math.CA2026

Lower bounds in -rational approximation to Blaschke products

Laurent Baratchart, Alexander Borichev, Sylvain Chevillard +2

We derive lower bounds in best rational approximation of given degree to finite Blaschke products, in the Hardy space of the unit disk. We first consider approximation to $z^…

math.OC2025

Notes on the discretization of TV-NORM regularized inverse potential problems

L Baratchart, D P Hardin, C Villalobos-Guillén +1

We describe a method to discretize optimization problems arising in the regularization of linear inverse problem having compact forward operator defined on 3-D valued measures, com…

cs.LG2024★ 18 cited

Croissant: A Metadata Format for ML-Ready Datasets

Mubashara Akhtar, Omar Benjelloun, Costanza Conforti +28

Data is a critical resource for machine learning (ML), yet working with data remains a key friction point. This paper introduces Croissant, a metadata format for datasets that crea…

cs.CL2023★ 18 cited

Energy and Carbon Considerations of Fine-Tuning BERT

Xiaorong Wang, Clara Na, Emma Strubell +2

Despite the popularity of the `pre-train then fine-tune' paradigm in the NLP community, existing work quantifying energy costs and associated carbon emissions has largely focused o…

cs.CV2023★ 8 cited

LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance

Linoy Tsaban, Apolinário Passos

Recent large-scale text-guided diffusion models provide powerful image-generation capabilities. Currently, a significant effort is given to enable the modification of these images…