Metraipolis › archive › dc_f5d3be8cd5d5

Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features — arXiv:2608.06008

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06008
License (as archived)
CC0-1.0
Archived
2026-10-31T10:38:19.711Z
SHA-256 of the archived text
3f45e8f7a7407034acd839c044299cdcad5094bae1e2fbcec77dcb2420b4fde4
Stable URL of this page
https://metraipolis.com/documento/dc_f5d3be8cd5d5

How to cite

Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features — arXiv:2608.06008 — arXiv (en), https://arxiv.org/abs/2608.06008 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5d3be8cd5d5 (Metraipolis archive dc_f5d3be8cd5d5, sha256 3f45e8f7a7407034acd839c044299cdcad5094bae1e2fbcec77dcb2420b4fde4)
BibTeX
@misc{dcf5d3be8cd5d5,
  title = {Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features — arXiv:2608.06008},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06008},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5d3be8cd5d5; sha256 3f45e8f7a7407034acd839c044299cdcad5094bae1e2fbcec77dcb2420b4fde4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06008. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large video diffusion models provide rich spatiotemporal priors for autonomous driving, but existing world-action models often inherit the cost of iterative future-video generation even though deployment only requires an ego trajectory. We ask a more basic question: how much of a video diffusion model must be executed to make a reliable driving decision? Through a controlled study of video denoising timesteps and Diffusion Transformer (DiT) depth, we find that planning performance is largely insensitive to the tested video-noise levels, whereas strong trajectories can already be decoded from intermediate layers. Based on this observation, we introduce Adaptive-WAM, a quality-aware multi-exit planner built on a Wan2.2-5B backbone. Trajectory diffusion heads are attached to selected DiT blocks, and a lightweight trajectory-quality scorer terminates inference once the best trajectory decoded so far satisfies a quality threshold; otherwise, computation continues from the cached hidden state to a deeper exit. The deployed planner therefore avoids the iterative classifier-free denoising loop and VAE decoding required for future-video synthesis, while dynamically allocating backbone depth according to trajectory quality. On NAVSIM, the adaptive single-trajectory planner achieves 90.8 PDMS; a separate fixed-exit variant reaches 92.6 PDMS with 64 proposals. It further obtains 89.9 EPDMS on NAVSIM v2, yielding the best reported results among the compared front-view video world-model planners. Without target-domain fine-tuning, Adaptive-WAM transfers to nuScenes with 0.88 m average L2 error and a 0.08\% collision rate. On an A100, adaptive routing improves PDMS from 90.62 to 90.79 while averaging 170 ms end-to-end planning latency, approximately 10\% below the 190 ms fixed block-15 planner and 47\% below the 320 ms fixed full-depth planner. Code will be released.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.06008 — 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 2026-10-31T10:24:02.121Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).