用一句话让机器人想象未来画面
你给机器人说一句“把杯子推到左边”，它就能生成一段视频，展示接下来几秒会发生什么——杯子真的被推过去了。这不是真的在动，而是机器人在脑子里“想象”出来的物理世界。Qwen-RobotWorld 把自然语言当作统一遥控器，让同一个模型能预测机械臂、自动驾驶、室内导航等不同场景的未来画面。它靠一个60层双流扩散变压器，把语言和视频特征一层层融合，再喂进860万条视频-文本数据训练。结果在多个评测榜上排第一。它不是你明天就能用的产品，但它是让机器人学会“预演”动作后果的关键一步——就像人类做决定前先脑补一下。
📄 原文摘要(英文)
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.