Search papers, labs, and topics across Lattice.
2
0
3
Graph-based code representations, largely unexplored in automated patch correctness assessment, crush sequence- and heuristic-based methods, achieving 82.6% accuracy in predicting patch correctness.
LLM-powered test generation can finally achieve meaningful coverage in deep learning libraries, thanks to a novel agent-driven framework that iteratively refines tests based on constraint validation.
