Metraipolis › archive › dc_726649983ed7
Scaling Action-Free Video Latent Prediction for Transferable Representations in End-to-End Autonomous Driving — arXiv:2611.02853
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02853
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:55:11.978Z
- SHA-256 of the archived text
4d75fce7530673009e28898011ff25a5ae7c637d39accf5f438c5269c8e97c9a- Stable URL of this page
https://metraipolis.com/documento/dc_726649983ed7
How to cite
Scaling Action-Free Video Latent Prediction for Transferable Representations in End-to-End Autonomous Driving — arXiv:2611.02853 — arXiv (en), https://arxiv.org/abs/2611.02853 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_726649983ed7 (Metraipolis archive dc_726649983ed7, sha256 4d75fce7530673009e28898011ff25a5ae7c637d39accf5f438c5269c8e97c9a)
BibTeX
@misc{dc726649983ed7,
title = {Scaling Action-Free Video Latent Prediction for Transferable Representations in End-to-End Autonomous Driving — arXiv:2611.02853},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02853},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_726649983ed7; sha256 4d75fce7530673009e28898011ff25a5ae7c637d39accf5f438c5269c8e97c9a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02853. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
End-to-end autonomous driving policies require effective visual representations that capture both spatial scene structure and temporal dynamics. Video latent prediction has emerged as an effective paradigm for learning spatiotemporal visual representations, yet it remains unclear whether scaling this objective with action-free driving videos can yield representations that benefit end-to-end planning. We study action-free video latent prediction as a scalable pretraining objective and introduce ScaleDrive, a driving-oriented framework pretrained exclusively on large-scale internet open-world driving videos, without action annotations or benchmark-specific data. We keep the pretrained video encoder frozen during downstream end-to-end planning training to isolate the transferability of representations learned from internet driving videos. Ego-motion and depth probes show that scaling action-free video pretraining progressively strengthens the temporal and geometric information encoded in the frozen representation. We systematically study the visual representation transfer across different end-to-end driving policies and closed-loop benchmarks, where ScaleDrive consistently improves downstream performance and demonstrates that scaling action-free video latent prediction yields representations that generalize across both planning policy architectures and evaluation scenarios and protocols. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.02853 — 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 2026-11-03T18:16:53.030Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).