Metraipolis › archive › dc_d03cb2f476e4

Rethinking Language's Role in Efficient VLA for Autonomous Vehicles: Toward Smarter, Trustworthy Driving — arXiv:2608.30144

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30144
License (as archived)
CC0-1.0
Archived
2026-10-17T10:06:53.818Z
SHA-256 of the archived text
bdbd4af9b9548a6697052a40039b4b0f9a369f45350357210a393d9b0a022ffd
Stable URL of this page
https://metraipolis.com/documento/dc_d03cb2f476e4

How to cite

Rethinking Language's Role in Efficient VLA for Autonomous Vehicles: Toward Smarter, Trustworthy Driving — arXiv:2608.30144 — arXiv (en), https://arxiv.org/abs/2608.30144 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d03cb2f476e4 (Metraipolis archive dc_d03cb2f476e4, sha256 bdbd4af9b9548a6697052a40039b4b0f9a369f45350357210a393d9b0a022ffd)
BibTeX
@misc{dcd03cb2f476e4,
  title = {Rethinking Language's Role in Efficient VLA for Autonomous Vehicles: Toward Smarter, Trustworthy Driving — arXiv:2608.30144},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30144},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d03cb2f476e4; sha256 bdbd4af9b9548a6697052a40039b4b0f9a369f45350357210a393d9b0a022ffd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30144. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) models are reshaping autonomous driving (AD) by unifying perception, reasoning, and control through language, enabling semantic grounding, interpretable decisions, and better long-tail generalization. But language is expensive onboard: latency and memory budgets are tight, and autoregressive decoding is inherently sequential. This work reframes the central question as when and where language should act at inference, since inference cost recurs at every deployed frame while training cost is paid once. We introduce the Language Residue taxonomy to organize methods by their inference-time use of language: train-time-only supervision (L1), latent non-textual reasoning (L2), conditional invocation (L3), and full per-frame generation (L4). We review representative methods and tag each across five deployment axes (latency, parameters, memory, FLOPs, tokens), analyzing them on major open- and closed-loop driving benchmarks (e.g., nuScenes, NAVSIM, Bench2Drive). We further trace how efficient methods from NLP/LLM are adapted in AD, identifying the constraints and motivations driving these adaptations. A continuously updated repository will be available at Github.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.30144 — 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 2026-10-17T09:58:57.801Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).