Search papers, labs, and topics across Lattice.
4
0
3
3
Bug reports that work for humans can actually hinder AI agents, with localization cues being critical for repair success.
PAW transforms how we build and execute functions, enabling efficient local execution of complex tasks with minimal resource overhead.
TestEvo-Bench exposes the stark reality that even advanced test automation agents struggle with recent code changes, achieving lower success rates in real-world scenarios.
Code2LoRA achieves high performance in code comprehension and adaptation with zero inference-time overhead, revolutionizing how we handle repository-specific knowledge in code language models.
