MIT Technology Review

Using unstructured data to fuel enterprise AI success

Organizations have a wealth of unstructured data that most AI models can’t yet read. Preparing and contextualizing this data ...
IEEE

Frequency Domain Transformation and Loss Adjustment for Enhancing Transferability of Adversarial Examples

Abstract: Due to the exponential disparity in the magnitude of high- and low-frequency components in the image frequency domain, existing frequency-domain enhancement methods for adversarial examples ...
IEEE

Learning to Transform: Evaluating LLMs on Model Transformation by Example

Abstract: Large language models have shown promising potential in reducing the accidental complexity of model-driven engineering, particularly in automating model transformation tasks. However, ...
Microsoft

Learning String Transformations from Examples

“Robert” and “Bob” refer to the same first name but are textually far apart. Traditional string similarity functions do not allow a flexible way to account for such synonyms, abbreviations and aliases ...