Metraipolis › archive › dc_16e301171dad
LIRA: Local Cross-Layer Information Routing for Vision-Language-Action Decoding — arXiv:2608.07596
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.07596
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:12:23.083Z
- SHA-256 of the archived text
345499389573ac08c45342314125b8dfb9581e242792b1311661e5e518eff2d4- Stable URL of this page
https://metraipolis.com/documento/dc_16e301171dad
How to cite
LIRA: Local Cross-Layer Information Routing for Vision-Language-Action Decoding — arXiv:2608.07596 — arXiv (en), https://arxiv.org/abs/2608.07596 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_16e301171dad (Metraipolis archive dc_16e301171dad, sha256 345499389573ac08c45342314125b8dfb9581e242792b1311661e5e518eff2d4)
BibTeX
@misc{dc16e301171dad,
title = {LIRA: Local Cross-Layer Information Routing for Vision-Language-Action Decoding — arXiv:2608.07596},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.07596},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_16e301171dad; sha256 345499389573ac08c45342314125b8dfb9581e242792b1311661e5e518eff2d4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07596. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language-Action (VLA) models transform representations from pretrained vision-language models (VLMs) into robot actions, yet the interface that routes intermediate VLM features into action decoders remains underexplored. Existing designs either expose only a narrow part of the representation hierarchy or rigidly match each decoder block to one VLM layer, restricting access to complementary task evidence across depths. We introduce LIRA, a local cross-layer action-conditioning mechanism that formulates VLM-to-action conditioning as depth-aware information routing. LIRA operates on task-token features and LIRA Query features derived from intermediate VLM states, then assigns each Parallel Fusion Block a depth-aligned local window centered on its corresponding VLM layer. Parallel Fusion Blocks aggregate neighboring LIRA Query features and integrate them with task-token features and proprioceptive inputs before action prediction. This routing interface leaves the backbone architecture, action decoder, and supervised training recipe unchanged. Across LIBERO, LIBERO-Plus, CALVIN ABC$\rightarrow$D, and real-world manipulation, LIRA improves the principal aggregate metrics over the VLA-Adapter baseline under the same 0.5B-parameter configuration. In zero-shot transfer to LIBERO-Plus, LIRA increases average success from 59.1% to 78.0%, an 18.9-point gain indicating improved robustness under controlled distribution shifts. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in cs.RO). Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.07596 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T09:11:58.720Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).