Search papers, labs, and topics across Lattice.
4
0
4
6
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.
Safe-RULE effectively neutralizes data poisoning threats in offline Safe RL, enhancing safety without the need for retraining from scratch.
Real-world cyber-physical system resilience demands a holistic approach integrating hardware, software, human factors, proactive measures, and adaptive recovery, moving beyond traditional fault models.
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.
