Search papers, labs, and topics across Lattice.
2
0
3
0
The results suggest that dense to MoE adaptation with dynamic expert deactivation is a practical direction for reducing active VLA model size without severe performance loss.
Agent memory can be compressed by 50% with virtually zero performance degradation (retaining up to 99.7% accuracy) and a 2x retrieval speedup by structuring historical context into event-centric maximum spanning trees.
