注册并分享邀请链接,可获得视频播放与邀请奖励。

Rapidata
@RapidataAI
Your one stop shop for real human data annotations, feedback and opinions.
加入 June 2024
156 正在关注    111 粉丝
Complex camera trajectories expose the gap between video models and world models. Sana WM from @nvidia + other world models move up. Typical video models start lagging. Check our camera motion benchmark: 14 models, 600 prompts, 145K human responses. Fully transparent and reproducible.
显示更多