Search papers, labs, and topics across Lattice.
2
0
5
Stop hand-engineering your multi-agent LLM systems: UnityMAS-O lets you train them end-to-end with RL, unlocking surprisingly large gains, especially for smaller models.
Forget storing full task-specific models – Auto-FlexSwitch compresses the knowledge into tiny, dynamically assembled task vectors, slashing storage costs without sacrificing accuracy.
