Search papers, labs, and topics across Lattice.
Affiliation:
5
1
7
8
Diverse LLMs, when strategically routed and collaborating, can collectively achieve significantly fairer outputs than any single model acting alone.
Mutation analysis as an adequacy metric for kernel-benchmark oracles is introduced: deterministic rules inject 10 compilable faults into verified CUDA implementations of 188 KernelBench problems, 7{,}384 of them with an independent kill witness; any test protocol is scored by the fraction it detects.
Efficiency in LLM-generated data science code can be drastically improved, even when correctness appears high, revealing hidden inefficiencies that traditional benchmarks overlook.
Ockhamareto achieves a staggering 49.9% mutation score while using 44% fewer tests than the best existing method, revolutionizing unit-test generation efficiency.
Learning high-level strategies can boost vulnerability reproduction success rates by over 20%, revolutionizing how we approach software security tasks.
