Metraipolis › archive › dc_f56cd04fef2e

Towards Reliable Vision-Language Models for Autonomous Driving — arXiv:2610.01531

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.01531
License (as archived): CC0-1.0
Archived: 2026-10-06T12:05:34.278Z
SHA-256 of the archived text: 4929c3907985cb06f184b592b5d6649c3c9525bfce7050403b1295c1c6dd32b0
Stable URL of this page: https://metraipolis.com/documento/dc_f56cd04fef2e

How to cite

Towards Reliable Vision-Language Models for Autonomous Driving — arXiv:2610.01531 — arXiv (en), https://arxiv.org/abs/2610.01531 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f56cd04fef2e (Metraipolis archive dc_f56cd04fef2e, sha256 4929c3907985cb06f184b592b5d6649c3c9525bfce7050403b1295c1c6dd32b0)

BibTeX

@misc{dcf56cd04fef2e,
  title = {Towards Reliable Vision-Language Models for Autonomous Driving — arXiv:2610.01531},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01531},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f56cd04fef2e; sha256 4929c3907985cb06f184b592b5d6649c3c9525bfce7050403b1295c1c6dd32b0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01531. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language models (VLMs) are increasingly being explored in autonomous driving for tasks such as scene understanding, driving reasoning, decision-making, and end-to-end driving. As their role becomes more prominent, ensuring their robustness and reliability is increasingly important. In real-world conditions, visual inputs may be degraded by sensor imperfections and environmental conditions, potentially affecting both model predictions and their associated confidence. Such degradation is especially concerning in autonomous driving, where safety-critical decisions require models to make accurate predictions and recognize when their predictions may be unreliable. In this work, we evaluate five VLMs (Qwen3.5-9B, Gemma4-E4B, LLaVA-OneVision-7B, DriveFusion/DriveFusionQA-4B, and NVIDIA Alpamayo-1.5-10B) across four driving-related QA datasets with different visual input settings, including single-frame, multi-view, multi-frame, and monocular inputs. Our results show that the effects of visual corruption vary across models, datasets, and input settings, with changes in accuracy and confidence reliability and also differing across conditions. We then apply Visual Evidence Augmentation ($\mathrm{V}{\scriptstyle \mathrm{EA}}$), a recent inference-time method to examine whether it can improve model reliability under degraded visual conditions. We find that $\mathrm{V}{\scriptstyle \mathrm{EA}}$ improves performance for some models and datasets, although the gains are not consistent across all settings.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.01531 — 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 2026-10-06T10:21:27.961Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).