Skip to content
DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation episode artwork

Aug 14, 2026 3 min

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

from Daily Paper Cast (Test) Hosted by Jingwen Liang, Gengyu Wang

🤗 Upvotes: 79 | cs.CV, cs.RO Authors: DreamX Team, Rui Chen, Xiangxiang Chu, Geng Li, Jifan Li, Qingfeng Shi, Datao Tang, Jing Tang, Jun Wang, Pengfei Zhang Title: DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation Arxiv: http://arxiv.org/abs/2608.13489v1 Abstract: 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.

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

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

0:00 3:52

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of Daily Paper Cast (Test)?

This episode is 3 minutes long.

When was this Daily Paper Cast (Test) episode published?

This episode was published on August 14, 2026.

Can I download this Daily Paper Cast (Test) episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.