titleQwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation
authorsJie Zhang, Xiaoyue Chen, Anzhe Chen, Chenxu Lv, Deqing Li, Gengze Zhou, Hang Yin, Haoqi Yuan, Haoyang Li, Jiahao Li, Jiazhao Zhang, Jingren Zhou, Kaiyuan Gao, Kun Yan, Lihan Jiang, Ningyuan Tang, Pei Lin, Qihang Peng, Shengming Yin, Tianhe Wu, Tianyi Yan, Xiao Xu, Yan Shu, Yanran Zhang, Ye Wang, Yi Wang, Yilei Chen, Yixian Xu, Yiyang Huang, Yuxiang Chen, Zekai Zhang, Zhendong Wang, Zhixing Lei, Zhixuan Liang, Zihao Liu, Zikai Zhou, Xiong-Hui Chen, Chenfei Wu
date2026-06-15
venuearXiv (preprint, not peer reviewed)
idarXiv:2606.17030
affiliationQwen
upvotes48 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf
primerWorld models
abstractWe 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 driving, indoor navigation, and human-to-robot transfer. This unified formulation provides three promising application directions: synthetic data generation for policy training augmentation, scalable virtual environments for policy evaluation, and language-guided planning signals for downstream robot control. This is achieved through a three-part design: a) Double-Stream MMDiT with MLLM Action Encoding, where a 60-layer double-stream diffusion transformer couples frozen Qwen2.5-VL semantics with video-VAE latents through layer-wise joint attention; b) Embodied World Knowledge (EWK), an 8.6M video-text corpus (200M+ frames) with action-language mapping over 20+ embodiments and 500+ action categories; and c) General+Expert Progressive Curriculum, a two-stage training strategy that first learns general visual priors and then injects embodied specialization under a shared language interface. Extensive results show strong competitiveness: ranks 1st overall on EWMBench and DreamGen Bench, outperforms all open-source models on WorldModelBench and PBench. Additional zero-shot analyses on RoboTwin-IF benchmark further support robust generalization and multi-view consistency.

cite

@misc{zhang2026qwen,
  title={Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation},
  author={Jie Zhang and Xiaoyue Chen and Anzhe Chen and Chenxu Lv and Deqing Li and Gengze Zhou and Hang 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 Zhixing Lei and Zhixuan Liang and Zihao Liu and Zikai Zhou and Xiong-Hui Chen and Chenfei Wu},
  year={2026},
  eprint={2606.17030},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2606.17030}
}