Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models

Vishaal Udandarao and Max Burg and Samuel Albanie and Matthias Bethge, International Conference on Learning Representations (ICLR), 2024
paper, code

@article{Udandarao2024DataTypes,
    author = "Udandarao, Vishaal and Burg, Max and Albanie, Samuel and Bethge, Matthias",
    title = "Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models",
    year = "2024",
    month = "January",
    journal = "International Conference on Learning Representations (ICLR)"
}