Metraipolis › archive › dc_76d7bfde40e7

RoboSTAR: Next-Scale Autoregressive Sign Language Translation for Humanoid Robots — arXiv:2609.32250

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32250
License (as archived)
CC0-1.0
Archived
2026-10-07T23:50:48.613Z
SHA-256 of the archived text
02dee751a8ab3cef84dcddb822f0f63aa7b902a813fd08f74902675ba442b3fd
Stable URL of this page
https://metraipolis.com/documento/dc_76d7bfde40e7

How to cite

RoboSTAR: Next-Scale Autoregressive Sign Language Translation for Humanoid Robots — arXiv:2609.32250 — arXiv (en), https://arxiv.org/abs/2609.32250 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_76d7bfde40e7 (Metraipolis archive dc_76d7bfde40e7, sha256 02dee751a8ab3cef84dcddb822f0f63aa7b902a813fd08f74902675ba442b3fd)
BibTeX
@misc{dc76d7bfde40e7,
  title = {RoboSTAR: Next-Scale Autoregressive Sign Language Translation for Humanoid Robots — arXiv:2609.32250},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32250},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_76d7bfde40e7; sha256 02dee751a8ab3cef84dcddb822f0f63aa7b902a813fd08f74902675ba442b3fd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32250. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sign-language interpretation in public communication relies on qualified professional interpreters and can be difficult to scale, motivating robotic signing as a complementary accessibility interface. We present RoBoSTAR, a text-conditioned sign language production (SLP) framework for generating human-centric sign motion that can be retargeted for robotic execution, with speech supported optionally through an external ASR front end. Conventional autoregressive approaches flatten motion into a single full-resolution token sequence, forcing long-range and local dependencies to be modeled at a uniform temporal granularity. RoBoSTAR instead combines part-wise Finite Scalar Quantization with next-scale autoregression, generating motion over progressively finer temporal resolutions while predicting synchronized body and hand tokens in parallel within each step. This coarse-to-fine formulation provides compact long-range context before progressively refining motion details, while self-conditioning and context corruption improve robustness to cross-scale prediction errors. The generated motion is subsequently retargeted for physical humanoid execution. Extensive qualitative and quantitative evaluations are conducted to demonstrate the effectiveness of RoBoSTAR.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.32250 — 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 2026-10-07T23:29:26.992Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).