Search papers, labs, and topics across Lattice.
4
0
7
4
By decoupling high-level reasoning from low-level control, Agentic Fast-Slow Planning enables more robust autonomous navigation, improving lateral deviation by up to 45% and completion time by over 12% compared to traditional MPC methods.
Dummy Class defenses, which appear robust under standard adversarial attacks, crumble when targeted with a novel attack that considers the "dummy" class as a valid target.
LLMs can navigate more efficiently in unfamiliar environments by reasoning over a tree of possible paths, not just isolated waypoints, enabling them to consider en-route information gain and prune unpromising branches.
Robots that learn from their mistakes *while* navigating? SERP unlocks this by evolving the action model in-context during replanning, boosting success rates and cutting token costs.
