arXiv Computer Vision
Spatially Aware World Action Model via Geometric Latent Diffusion
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Aug 6
LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models
World models enable agents to perform forward rollout and planning without real-world interaction. However, their application in open-world embodied intelligence remains limited by the high cost of action annotations and the heterogeneity of action spaces across platforms.
arXiv AI
Aug 25
Inferring Action from Future Latent State for Robotic Manipulation
arXiv:2608.22067v1 Announce Type: cross Abstract: World-Action Models (WAMs) build robot control on video-generation backbones, which jointly predict dense future visual trajectories and robot action...
arXiv Machine Learning
Jun 16
Geometric Action Model for Robot Policy Learning
arXiv:2606. 17046v1 Announce Type: cross Abstract: Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot actions interact in the 3D physical world.
arXiv AI
Aug 27
DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation
DELE-w0.5 is a robotic manipulation framework that predicts future latent states instead of generating full video sequences, thereby inferring robot actions directly from these compact representations. By focusing on physical state changes rather than visual transitions, it reduces model complexity and inference latency. In 480 real‑robot trials across four long‑horizon tasks, DELE‑w0.5 achieved 62.5 % overall task success and 81.3 % macro ordered‑stage progress, outperforming the strongest baseline by 47.5 and 30.7 percentage points.
arXiv AI
Aug 5
UniNav: A Unified World-Action Diffusion Model for Visual Navigation
arXiv:2608. 03244v1 Announce Type: new Abstract: Image-goal visual navigation is a fundamental capability for embodied agents.
arXiv Computer Vision
2d ago
ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training
ZimaBlue is a scalable framework that learns generalizable World Action Models (WAMs) from large-scale egocentric videos. It follows a three-stage curriculum: causal video pre‑training, video‑action mid‑training with a unified action representation, and final specialization to a target robot. The system employs an asynchronous Slow‑Fast architecture to enable real‑time 30 Hz action prediction, achieving a jump in real‑robot zero‑shot success from 36.1% to 77.8% when leveraging over 120,000 hours of embodied video.