Metraipolis › archive › dc_d1535b17ecbb
DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation — arXiv:2609.24976
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24976
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T22:06:40.777Z
- SHA-256 of the archived text
bf22f25fcb35fecb07c1f6a2be52d23b393373e6c318a720d39ebded2999f914- Stable URL of this page
https://metraipolis.com/documento/dc_d1535b17ecbb
How to cite
DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation — arXiv:2609.24976 — arXiv (en), https://arxiv.org/abs/2609.24976 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d1535b17ecbb (Metraipolis archive dc_d1535b17ecbb, sha256 bf22f25fcb35fecb07c1f6a2be52d23b393373e6c318a720d39ebded2999f914)
BibTeX
@misc{dcd1535b17ecbb,
title = {DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation — arXiv:2609.24976},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24976},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d1535b17ecbb; sha256 bf22f25fcb35fecb07c1f6a2be52d23b393373e6c318a720d39ebded2999f914},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24976. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dexterous manipulation depends on contact dynamics that are often only partially observable from vision. Recent World-Action Models (WAMs) couple predictive video world modeling with action generation, but remain largely vision-centric and therefore cannot directly model these contact dynamics. We present DexTacWAM, a visuo-tactile WAM that encodes each fingertip independently, aggregates the resulting features through a finger- and pose-aware tactile compressor, and injects the tactile latent into a video diffusion world model for joint visuo-tactile world modeling. Across six contact-rich dexterous manipulation tasks on a 22-DoF bimanual platform, DexTacWAM achieves the highest score on every task, averaging 70.6 versus 38.0 for the strongest baseline. Ablations attribute the gain to modeling contact evolution as part of the predicted world state rather than tactile conditioning alone: removing tactile world modeling reduces the four-task mean from 74.7 to 26.6 while keeping the same tactile features and action expert. After four hours of tactile-encoder adaptation with a frozen pretrained vision VAE, our continual vision-to-touch learning extends the pretrained video model to touch using roughly 100 demonstrations per task without tactile midtraining, while retaining visual prediction quality within 0.5 dB of vision-only counterparts. The compressor retains 89.4% of pre-fusion contact recall while enabling 2.26x faster training and 1.29x faster inference. Together, these results show that pretrained video priors can be extended to distributed multi-finger contact dynamics in a data- and compute-efficient manner. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.24976 — 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 2026-10-09T21:45:21.161Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).