LectureRechercheRadarCadre d'investissement
Connexion / Inscription
← Retour à la lecture
ActualitésPrise rapide1 min de lectureRédaction DisconfirmAI

DiffAdapterVLA embeds trajectory tokens into driving VLM late layers, low latency and few parameters on NAVSIM

DiffAdapterVLA injects explicit trajectory tokens into the late layers of a driving vision-language model, with authors self-reporting high closed-loop planning quality, low latency and few trainable parameters on NAVSIM.

2026-09-23 12:00 GMT+8

DiffAdapterVLA injects explicit trajectory tokens into the late layers of a driving vision-language model, letting trajectory states co-evolve with driving conditions during the backbone's forward computation while training only lightweight adapter modules; the authors self-report high closed-loop planning quality, low latency and few trainable parameters on the NAVSIM benchmark.

Previous approaches did not let trajectory states co-evolve with driving conditions in the backbone's forward computation, making it hard to balance planning quality, latency and parameter count.

The measurement was done first-party by Changxin Lu and seven co-authors: on the NAVSIM benchmark they self-report high closed-loop planning quality, low latency and few trainable parameters.

Boundary: results are author self-reported with no third-party reproduction yet; the preprint was submitted to arXiv on September 14 (v2 updated on the 16th, arXiv:2609.15322).

Sources

  • arxiv.org↗
Continuer la recherche →
Connexion / Inscription
LectureRechercheRadarCadre d'investissement