Qwen-RobotManip: Alignment Unlocks Scale for Robotic Manipulation Foundation Models

From the source

Qwen-RobotManip is a generalizable Vision-Language-Action (VLA) foundation model built upon Qwen-VL. It introduces a unified alignment framework across the representation, motion, and behavioral dimensions of manipulation, making large-scale multi-source training coherent rather than conflicting. Using only open-source robotic manipulation datasets and human demonstration videos without any proprietary data collection, Qwen-RobotManip constructs a ~38,100 hours pretraining corpus and already exhibits emergent generalization capabilities.

qwen.ai