Search papers, labs, and topics across Lattice.
2
1
6
2
Multi-agent LLM systems are leaving performance on the table by treating structured agent interactions as generic traffic; Pythia shows how to unlock substantial gains by exploiting workflow semantics at the serving layer.
Robots learn better when they first imagine the future and then figure out how to act, unlocking SOTA performance by disentangling forward and inverse dynamics pretraining.
