Odyssey 发布世界模型 Odyssey-3，开放研究预览
Odyssey-3 能根据一句话生成可实时走动的交互世界，还接上了机器人和真车，Physics-IQ 拿了最高分，挺值得试试预览版。
Odyssey 推出基础世界模型 Odyssey-3，可根据提示词构建环境，并实时预测人物移动或事件触发后的场景变化。Odyssey-3 Pro 在 Physics-IQ Verified 视频-视频基准上取得 66.1 分（best-of-8 采样），为目前最高 reported 成绩。用户能以第一或第三人称在场景中行走，相机也可独立运动。该模型还被适配到机械臂、人形机器人和一辆在印度真实道路上行驶的汽车，每个系统使用各自训练的策略。
Odyssey has launched Odyssey-3, its most powerful foundation world model to date, and opened a research preview to the public.
Odyssey-3 builds an environment from a prompt and predicts changes in real time as a person moves through it or triggers events.
> Odyssey-3 Pro scored 66.1 on Physics-IQ Verified video-to-video with best-of-8 sampling. This is the highest reported result.
> Users can walk through scenes in first or third person. The camera can also move independently.
> Odyssey adapted the model to robot arms, humanoids, and a car on real roads in India. Each system uses its own trained policy.
