研究人员推出了 Qwen-RobotWorld，一个新颖的、用于具身智能的语言条件视频世界模型。该模型利用双流扩散 Transformer 和广泛的具身世界知识语料库，来预测各种机器人领域的未来视觉轨迹。Qwen-RobotWorld 表现强劲，在 EWMBench 和 DreamGen Bench 等基准测试中名列前茅，并在 WorldModelBench 和 PBench 上超越了其他开源模型。 AI
影响 该模型有望通过提供一个统一的框架来跨不同机器人任务进行训练和评估，从而加速具身 AI 的发展。
排序理由 该集群包含一份技术报告，详细介绍了一个新的人工智能模型及其在基准测试上的表现，符合研究类别。
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
By treating natural language as a universal action interface，Qwen-RobotWorld bridges the gap between general video generation models and domain-specific embodied models — this converts end-effector poses, steering commands, and navigation waypoints into a single interface, https…
Embodied intelligence requires agents to perceive, reason about, and act within physical environments. World models offer a scalable path forward — but current approaches face a fundamental tension. General video generation models learn rich visual priors but lack the ability to …
Qwen-RobotWorld is a language-conditioned video world model that predicts future visual trajectories across multiple robotic domains using a double-stream diffusion transformer and embodied world knowledge corpus.
arXiv:2606.17030v1 Announce Type: new Abstract: 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 observati…
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 driv…