Search papers, labs, and topics across Lattice.
2
0
2
0
Mid-generation intervention during LRLM inference can preserve valid robotic plans and correct errors, boosting success rates and efficiency beyond one-shot or iterative refinement alone.
LLMs can generate better unit tests for complex code by iteratively removing already-covered code, simplifying the generation task and boosting coverage beyond state-of-the-art methods.
