Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
19
A search-based metamorphic testing approach that identifies a minimal set of transformations on underwater images to induce incorrect model predictions, thereby revealing VLM failures and derive lessons for software engineering practitioners and researchers working on quality assurance of VLM-based software systems.
LLMs may not be the silver bullet for automated program repair, as their integration can lead to worse performance than traditional methods.
Minimizing failure-inducing test inputs can paradoxically increase failure reproducibility in stochastic environments, transforming how we debug Cyber-Physical Systems.
Metamorphic Testing offers a surprisingly effective, oracle-free approach to uncovering failures in vision-language-action robots, even detecting subtle issues like uncompleted tasks.
