Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
4
16
Shared experts in MoEs paradoxically limit the very exploration fine-grained segmentation needs, but MirrorMoE unlocks this potential by adaptively pruning the routing space.
This work presents Co-VLA, which applies consensus optimization using the Alternating Direction Method of Multipliers~(ADMM) to federated VLA training, and demonstrates that Co-VLA achieves performance comparable to centralized training in both full-model training and parameter-efficient fine-tuning settings.