Search papers, labs, and topics across Lattice.
Affiliation:
5
0
4
0
LLMs struggle to generate effective Triton kernels even when evaluated in realistic, production-like scenarios, revealing a critical gap in their practical applicability.
DyRetriever achieves a remarkable 25.63% improvement in code generation accuracy while slashing retrieval times by over 7x compared to traditional methods.
Quality-aware code search can significantly boost developer productivity by prioritizing high-quality code that meets specific resource optimization needs.
PracRepair fixes 162 out of 171 bugs in a challenging benchmark, showcasing a leap in automated program repair capabilities through human-inspired debugging techniques.
Python regression testing just got a whole lot faster and safer: NameRTS skips nearly 70% of tests while rarely missing affected ones, blowing away existing file-level dependency methods.
