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