@article{zhang2026qwenrobotworld,
  title={Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation},
  author={Zhang, Jie and Chen, Xiaoyue and Chen, Anzhe and Li, Deqing and Zhou, Gengze and Yin, Hale and Yuan, Haoqi and Li, Haoyang and Li, Jiahao and Zhang, Jiazhao and Zhou, Jingren and Gao, Kaiyuan and Yan, Kun and Jiang, Lihan and Tang, Ningyuan and Lin, Pei and Peng, Qihang and Yin, Shengming and Wu, Tianhe and Yan, Tianyi and Xu, Xiao and Shu, Yan and Zhang, Yanran and Wang, Ye and Wang, Yi and Chen, Yilei and Xu, Yixian and Huang, Yiyang and Chen, Yuxiang and Zhang, Zekai and Wang, Zhendong and Lei, Zixing and Liang, Zhixuan and Liu, Zihao and Zhou, Zikai and Lv, Chenxu and Chen, Xiong-Hui and Wu, Chenfei},
  journal={arXiv preprint arXiv:2606.17030},
  year={2026}
}