Metraipolis › archive › dc_7393fec8fa27

DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation — arXiv:2608.13489

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13489
License (as archived)
CC0-1.0
Archived
2026-10-19T04:55:57.867Z
SHA-256 of the archived text
4a2cf66edda3ca934d1878a90cdc0d33aa67fb722b345a98ce8d5fa92cd51ec1
Stable URL of this page
https://metraipolis.com/documento/dc_7393fec8fa27

How to cite

DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation — arXiv:2608.13489 — arXiv (en), https://arxiv.org/abs/2608.13489 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7393fec8fa27 (Metraipolis archive dc_7393fec8fa27, sha256 4a2cf66edda3ca934d1878a90cdc0d33aa67fb722b345a98ce8d5fa92cd51ec1)
BibTeX
@misc{dc7393fec8fa27,
  title = {DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation — arXiv:2608.13489},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13489},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7393fec8fa27; sha256 4a2cf66edda3ca934d1878a90cdc0d33aa67fb722b345a98ce8d5fa92cd51ec1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13489. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present \textbf{DreamX-Phi 1.0}, an action-conditioned video world model for robotic manipulation that, given an observed frame, a language instruction, and a prescribed action sequence comprising end-effector poses and gripper states, predicts the resulting future observations. Yet realism alone does not guarantee faithfulness: a convincing rollout can still move the wrong arm or lose the manipulated object. To ensure the prediction respects each arm's commanded path, we inject per-arm $\mathrm{SE}(3)$ transformations into attention via \textbf{PRoPE-style geometric encoding}, preserving arm identity and rigid-motion structure. Action control alone does not fully constrain scene geometry or the evolution of small manipulated objects. We therefore add a lightweight \textbf{depth branch} for scene-level geometry and use \textbf{SAM3 masks} with a frozen \textbf{V-JEPA teacher} to maintain object consistency throughout grasping. We further distill the multi-step generator into a few-step student via distribution-matching distillation for efficient deployment. At the time of writing, \model{} achieves first place on Track~1 and second place on Track~2 of the WorldArena~2.0 Challenge. Our model and code will be publicly available.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.13489 — 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 2026-10-19T04:46:30.251Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).