Metraipolis › archive › dc_aae80803bc9a
TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models — arXiv:2610.00899
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00899
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:11:42.860Z
- SHA-256 of the archived text
9b4a84128ddc088e72bfd23b4423773cbb460db4cb97a06ae1af35d49acaaeb4- Stable URL of this page
https://metraipolis.com/documento/dc_aae80803bc9a
How to cite
TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models — arXiv:2610.00899 — arXiv (en), https://arxiv.org/abs/2610.00899 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aae80803bc9a (Metraipolis archive dc_aae80803bc9a, sha256 9b4a84128ddc088e72bfd23b4423773cbb460db4cb97a06ae1af35d49acaaeb4)
BibTeX
@misc{dcaae80803bc9a,
title = {TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models — arXiv:2610.00899},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00899},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aae80803bc9a; sha256 9b4a84128ddc088e72bfd23b4423773cbb460db4cb97a06ae1af35d49acaaeb4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00899. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Autoregressive Vision-Language-Action models often represent continuous robot actions as discrete token sequences, enabling action prediction with standard next-token objectives. FAST has substantially improved this representation by compactly encoding action containing diverse temporal frequencies into relatively few tokens. However, while such compression reduces the number of action tokens required for autoregressive prediction, it does not necessarily improve the efficiency of policy learning from limited demonstrations. In particular, FAST typically assigns a single deterministic tokenization to each quantized action sequence, although multiple token sequences can represent and decode to the same robot motion. We investigate whether exploiting this representational redundancy can improve policy learning. In this paper, we propose TOkenization of Action sequences with STochastic sampling (TOAST), a stochastic action tokenization method that samples alternative tokenizations of the same quantized action sequence during policy training. This diversifies the discrete supervision while preserving the underlying robot action and requires no additional demonstrations. Experiments on LIBERO show that TOAST consistently improves over its deterministic counterpart, with the improvement increasing as training data decreases, achieving a 6.8 point gain in success rate when only 1/16 of training data is available. Across four real-robot manipulation tasks, TOAST further improves mean success rate by 15.8 points over the deterministic counterpart. These results demonstrate the effectiveness of stochastic action tokenization for autoregressive robot policy learning, particularly when training data are limited. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.00899 — 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 2026-10-06T10:21:28.126Z 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).