Search papers, labs, and topics across Lattice.
Technical University of Munich & fortiss GmbH
2
0
6
LLMs can automate web testing Page Object generation with over 70% element recognition, but still struggle with accuracy, revealing key areas for improvement in integrating LLMs into practical testing workflows.
Regularizing GAN latent spaces with code mixing and binary search can significantly boost the fault-finding ability of generated test inputs for deep learning classifiers.
