Search papers, labs, and topics across Lattice.
2
0
4
0
Fusing MPC with RL yields safer and more efficient autonomous driving at intersections, outperforming both standalone MPC and end-to-end RL, and surprisingly generalizing better to new scenarios.
LLM agents can be tricked into ignoring user instructions and misusing tools in over 90% of trials via a new "Memory Control Flow Attack" that exploits persistent memory influence.
