AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

GaussianDream++: Efficient 3D Gaussian World Modeling for Robotic Manipulation

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Vision-Language-Action (VLA) policies have advanced language-conditioned robotic manipulation, yet action-imitation objectives provide only weak supervision for metric 3D structure and short-horizon physical evolution. Geometry-enhanced policies mainly improve current-scene grounding, whereas predictive policies often model future dynamics in RGB or latent spaces and may incur substantial deployment cost. GaussianDream demonstrates that training-time current Gaussian reconstruction and future Gaussian prediction provide effective 3D supervision, but its dense VGGT/TGE-based prefix jointly carr

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T09:22:01.459Z. This is not the publication date.