你走进一个世界，它同时生成画面、风声和对话
现在的世界模型大多只生成画面，你走进去，世界是哑的。EchoWM 把这件事做全了：你控制视角往前走，它实时生成 720p 视频、环境音、音乐、甚至角色说话，四样东西同步、不打架。关键设计是它把「你想怎么动」统一成一种 6 维轨迹(位置+朝向)，不管你是第一人称自己走，还是第三人称遥控角色，都转成同一套坐标，然后模型同时学画面和声音怎么跟着轨迹变。为了能长时间生成不崩，他们先用大量数据预训练，再用自回归方式微调长序列。测试下来，轨迹跟随和画质都达到当前最好水平，而且能保持几十秒内声音和画面同步。它不是你明天就能用的产品，但它是第一个让你觉得「走进一个活的世界」而不是「看一段预渲染视频」的模型。
📄 原文摘要(英文)
We present EchoWM, an omnimodal world model for enterable generative media that responds to continuous navigation while jointly generating 720p video, environmental sound, music and speech. We organize interaction around camera intent: in first-person scenes, it specifies observer motion, while in third-person scenes, camera--character dynamics are learned from data without view-specific controllers. Discrete commands and continuous poses are mapped to a shared metric-scale relative 6-DoF trajectory, with dataset-level calibration preserving motion magnitude across heterogeneous data. To jointly learn audio-visual generation and trajectory control, we construct a complementary data engine and adopt progressive training followed by autoregressive post-training for long-horizon generation. Extensive evaluations show that \model achieves strong trajectory following and high visual quality on public world-model benchmarks, supporting both first- and third-person interaction across varied subjects, and maintaining synchronized environmental sound and speech over long-horizon generation.