Preprint
Aug 2026
LIRA: Local Cross-Layer Information Routing for Vision-Language-Action Decoding
LIRA is introduced, a local cross-layer action-conditioning mechanism that formulates VLM-to-action conditioning as depth-aware information routing and improves the principal aggregate metrics over the VLA-Adapter baseline under the same 0.5B-parameter configuration.
Zhe-Wei Zhang, Pu Wang, Guan-Ren Qiao et al.
· 4 citations