activity
20242026
collaborators

8 papers

cs.CV2026

DataComp-VLM: Improved Open Datasets for Vision-Language Models

Matteo Farina, Vishaal Udandarao, Thao Nguyen +34

Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curat…

cs.CV2025

Concept-Aware Batch Sampling Improves Language-Image Pretraining

Adhiraj Ghosh, Vishaal Udandarao, Thao Nguyen +7

What data should a vision-language model be trained on? To answer this question, many data curation efforts center on the quality of a dataset. However, most of these existing meth…

cs.CV2025

Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic Data

Stefania L. Moroianu, Christian Bluethgen, Pierre Chambon +8

Achieving robust performance and fairness across diverse patient populations remains a challenge in developing clinically deployable deep learning models for diagnostic imaging. Sy…

cs.CV2025

A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks

Vishaal Udandarao, Mehdi Cherti, Shyamgopal Karthik +3

We investigate 17 benchmarks (e.g. SugarCREPE, VALSE) commonly used for measuring compositional understanding capabilities of vision-language models (VLMs). We scrutinize design ch…

cs.LG2025

Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets

Marianna Nezhurina, Tomer Porian, Giovanni Pucceti +4

In studies of transferable learning, scaling laws are obtained for various important foundation models to predict their properties and performance at larger scales. We show here ho…

cs.CV2025

Scalable heliostat surface predictions from focal spots: Sim-to-Real transfer of inverse Deep Learning Raytracing

Jan Lewen, Max Pargmann, Jenia Jitsev +3

Concentrating Solar Power (CSP) plants are a key technology in the transition toward sustainable energy. A critical factor for their safe and efficient operation is the distributio…