Search papers, labs, and topics across Lattice.
3
0
7
0
Weak models can supercharge strong models through efficient policy shift transfers, achieving significant performance gains without the usual rollout costs.
AOHP redefines how AI agents interact with operating systems, achieving a 21% boost in task completion and a dramatic cut in execution costs.
High-diversity training improves safety in VLA models, but sub-optimal trajectory synthesis still hinders task success.
