Metraipolis › archive › dc_a51766b4e2f3

SignGPT: Toward LLM-Mediated Sign Language Interaction through Gloss-Free Translation and Generation — arXiv:2609.21709

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21709
License (as archived)
CC0-1.0
Archived
2026-10-10T02:29:39.938Z
SHA-256 of the archived text
d13f224c15184da1e7021046f36dbcd5c68ebddde43148cecc17437c1c58a665
Stable URL of this page
https://metraipolis.com/documento/dc_a51766b4e2f3

How to cite

SignGPT: Toward LLM-Mediated Sign Language Interaction through Gloss-Free Translation and Generation — arXiv:2609.21709 — arXiv (en), https://arxiv.org/abs/2609.21709 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a51766b4e2f3 (Metraipolis archive dc_a51766b4e2f3, sha256 d13f224c15184da1e7021046f36dbcd5c68ebddde43148cecc17437c1c58a665)
BibTeX
@misc{dca51766b4e2f3,
  title = {SignGPT: Toward LLM-Mediated Sign Language Interaction through Gloss-Free Translation and Generation — arXiv:2609.21709},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21709},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a51766b4e2f3; sha256 d13f224c15184da1e7021046f36dbcd5c68ebddde43148cecc17437c1c58a665},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21709. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) provide limited support for sign language interaction. Unifying sign language translation (SLT) and generation (SLG) to enable sign language as both input and output can reduce switching between separate models during sign-text interaction. We present SignGPT, a unified, pose-based framework for gloss-free SLT and SLG. SignGPT integrates part-aware hierarchical representations of body, hand, and facial motion into a shared language model and employs asymmetric multi-token prediction and progressive training for bidirectional modeling. We evaluate SignGPT on How2Sign (ASL) and Phoenix-2014T (DGS) through benchmark comparisons, qualitative analyses, and component ablations. An exploratory study with 12 Deaf ASL signers assesses an LLM-mediated sign-to-sign response pipeline, highlighting the potential of unified modeling to support sign language conversation (SLC).

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.21709 — 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 2026-10-10T02:07:36.090Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).