By treating natural language as a universal action interface，Qwen-RobotWorld bridges the gap between general video generation models and domain-specific embodied models — this converts end-effector poses, steering commands, and navigation waypoints into a single interface, https…
Embodied intelligence requires agents to perceive, reason about, and act within physical environments. World models offer a scalable path forward — but current approaches face a fundamental tension. General video generation models learn rich visual priors but lack the ability to …
Qwen-RobotWorld is a language-conditioned video world model that predicts future visual trajectories across multiple robotic domains using a double-stream diffusion transformer and embodied world knowledge corpus.
arXiv:2606.17030v1 Announce Type: new Abstract: We introduce Qwen-RobotWorld, a language-conditioned video world model for embodied intelligence. With natural language as a unified action interface, it predicts physically grounded future visual trajectories from current observati…
We introduce Qwen-RobotWorld, a language-conditioned video world model for embodied intelligence. With natural language as a unified action interface, it predicts physically grounded future visual trajectories from current observations across robotic manipulation, autonomous driv…
<p>We break down Qwen-RobotSuite, the Qwen team's three new embodied AI models. We cover RobotManip, a Vision-Language-Action model built on Qwen3.5-4B for manipulation. We cover RobotWorld, a language-conditioned video world model with a 60-layer MMDiT. We cover RobotNav, a navi…
