Qwen-RobotManip: Alignment unlocks scale for robotic manipulation foundation models

Qwen-RobotManip：对齐解锁机器人操作基础模型的规模化能力

Qwen team released Qwen-RobotManip, a foundation model for robotic manipulation. The key insight: alignment, not just larger pretraining, is what makes scale pay off. Demos show cross-embodiment generalization across real robots—stacking bowls, folding clothes, making burgers, arranging flowers—with Qwen-Omni issuing open-ended voice commands on the fly, no predefined task list. The post does not disclose model size, training data scale, or latency figures; only demo videos and a paper link are provided.

Why it matters: Qwen-RobotManip isn't just another robotics model — it uses alignment instead of more pre-training data to unlock scale, with live demos where Qwen-Omni gives random voice commands and the arm executes on the fly. Score stays below 85 because the post doesn't disclose preferen...