Odyssey发布世界模型Odyssey-3,Pro版Physics-IQ得分
Odyssey released Odyssey-3, a world model whose Pro version posts the highest re…
全新世界模型发布且刷新了Physics-IQ基准记录,Flash版还提供免费体验入口,关注生成式AI与具身智能的同学值得第一时间了解。
Odyssey released Odyssey-3, a world model whose Pro version posts the highest reported Physics-IQ Verified video-to-video score, 66.1.
Odyssey 发布了 Odyssey-3,这是一个世界模型,其 Pro 版本在 Physics-IQ Verified 视频到视频评分中创下最高报告分数 66.1。
It's an autoregressive diffusion transformer that predicts next frames from earlier ones plus incoming actions, letting prompted scenes react to each move.
它是一个自回归扩散 Transformer,根据早期帧和传入的动作预测下一帧,使受提示的场景能对每个动作做出反应。
> Odyssey-3 Flash, a distilled few-step version, turns a text prompt into an explorable world that reacts to movement and events in real time, and anyone can try it free today.
> Odyssey-3 Flash 是一个经过蒸馏的少步数版本,能将文本提示转化为一个可探索的世界,实时响应运动和事件,任何人都可以免费试用。
> With Odyssey-3 frozen, a policy trained on 20 hours of Indian road data drove a real car, and a robot arm recovered from missed grasps its demos never showed, though neither result reports success rates.
> 在冻结 Odyssey-3 的情况下,基于 20 小时印度道路数据训练的策略驾驶了一辆真车,机械臂从从未在演示中出现过的错误抓取中恢复过来,尽管这两个结果均未报告成功率。
> on image-to-video Odyssey-3 Pro roughly ties FLUX 3 [large]
> 在图像到视频方面,Odyssey-3 Pro 大致与 FLUX 3 [large] 持平
更进一步:量化金融体系
看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力