paper-with-me

홈 › Papers

Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation

2026-06-15 · Jie Zhang, Xiaoyue Chen, Anzhe Chen, Dayiheng Liu, Deqing Li, Gengze Zhou, Hale 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, Zixing Lei, Zhixuan Liang, Zihao Liu, Zikai Zhou, Chenxu Lv, Xiong-Hui Chen, Chenfei Wu arxiv

We 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.

📄 PDF Abstract BibTeX arXiv:2606.17030

Code (0)

등록된 구현이 없습니다.

Tasks

Synthetic Data GenerationAutonomous DrivingVideo Generation

Similar Papers 제목 키워드 기반

Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interaction

2026-07-21 · Jialian Li, Junhong Liu, Yuchen Cao, Weiran Guo 외 arxiv

Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge. As embodied agents become increasingly capable, there is a growing demand for compact mode…

General Reinforcement Learning

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

2026-05-28 · Qiuyue Wang, Mingsheng Li, Jian Guan, Jinhui Ye 외 arxiv

Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks, environments, and r…

Trajectory PredictionSpatial ReasoningVisual Grounding

Qwen2.5-Coder Technical Report

2024-09-18 · Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang 외

In this report, we introduce the Qwen2.5-Coder series, a significant upgrade from its predecessor, CodeQwen1.5. This series includes six models: Qwen2.5-Coder-(0.5B/1.5B/3B/7B/14B/32B). As a code-specific model, Qwen2.5-…

Code GenerationMathSynthetic Data Generation

MiMo-Embodied: X-Embodied Foundation Model Technical Report

2025-11-20 · Xiaoshuai Hao, Lei Zhou, Zhijian Huang, Zhiwen Hou 외 arxiv

We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI. MiMo-Embodied sets new records across…

Autonomous Driving

RoboBrain 2.0 Technical Report

2025-07-02 · BAAI RoboBrain Team, Mingyu Cao, Huajie Tan, Yuheng Ji 외 arxiv

We introduce RoboBrain 2.0, our latest generation of embodied vision-language foundation models, designed to unify perception, reasoning, and planning for complex embodied tasks in physical environments. It comes in two …

Trajectory Forecasting