Metraipolis › archive › dc_141b912dfd55

All-For-One: Distilling Visual Foundation Models to a Fast, Memory-Efficient Visuomotor Policy — arXiv:2611.04485

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.04485
License (as archived): CC0-1.0
Archived: 2026-11-04T12:58:21.798Z
SHA-256 of the archived text: 8ae3bf36fea5d6212ff173e942fbef6de8c146293ca4da5045228e3fc78d3f72
Stable URL of this page: https://metraipolis.com/documento/dc_141b912dfd55

How to cite

All-For-One: Distilling Visual Foundation Models to a Fast, Memory-Efficient Visuomotor Policy — arXiv:2611.04485 — arXiv (en), https://arxiv.org/abs/2611.04485 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_141b912dfd55 (Metraipolis archive dc_141b912dfd55, sha256 8ae3bf36fea5d6212ff173e942fbef6de8c146293ca4da5045228e3fc78d3f72)

BibTeX

@misc{dc141b912dfd55,
  title = {All-For-One: Distilling Visual Foundation Models to a Fast, Memory-Efficient Visuomotor Policy — arXiv:2611.04485},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04485},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_141b912dfd55; sha256 8ae3bf36fea5d6212ff173e942fbef6de8c146293ca4da5045228e3fc78d3f72},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04485. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visual Foundation Models (VFMs) provide semantic cues such as depth and segmentation useful for robotic manipulation, but directly deploying them in closed-loop control is impractical due to high computational cost, temporal inconsistency, and distribution shift between static internet images and egocentric robot observations. We propose All-For-One (AFO), a two-stage distillation framework that leverages VFMs strictly as privileged information during training, using downstream robotic data. Following the privileged learning paradigm, AFO decouples semantic representation learning from inference-time policy execution. In the All stage, a teacher policy fuses RGB observations with outputs from multiple VFMs to learn a semantically enriched representation. In the For-One stage, this knowledge is distilled in-distribution into a lightweight RGB-only student policy. Evaluated on two Adroit tasks and five MetaWorld tasks in simulation, as well as three real-world manipulation tasks, AFO outperforms prior foundation-model-based approaches while using over 30x fewer parameters than VFM-based encoders and 50x lower latency than its own teacher in simulation benchmarks, providing an efficient pathway for transferring foundation-model knowledge to robotic control.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2611.04485 — 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 2026-11-04T12:34:02.090Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).