Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
Multi-agent LLM training falters when updates are decoupled from joint state transitions; grouping interacting agent outputs into cardinality-normalized set actions solves credit assignment across both static and dynamically routed systems.
Robotic world-action models do not need pretrained internet video backbones to scale: training native planning and dynamics modules from scratch across 30,000 hours unlocks strong zero-shot manipulation and drives a 17.7-point gain on an embodiment comprising under 2% of the data.
