DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
Alibaba Group
DreamX-Phi is a video world model that takes an observed frame, a language instruction, and an action sequence and predicts future robot-manipulation observations, using geometric attention injection, a depth branch, and SAM3-masked distillation from a frozen V-JEPA teacher for object consistency.
Why it matters
Placed 1st on Track 1 and 2nd on Track 2 of the WorldArena 2.0 Challenge; shows action-conditioned world models maturing as a practical tool for robot policy evaluation and data generation.
Importance: 2/5
Notable paper: competitive placement in a world-model benchmark challenge, official arXiv/HF source.
Sources
official
DreamX-Phi 1.0 on HF Daily Papers