Momentum: Persistent Dynamics for Video World Models
视频世界模型研究，未放权重，暂时用不上
Video world models must capture how a scene evolves beyond the current camera view to generate consistent observations when its content reappears. Existing approaches rely on observation history, static point clouds, or image caches constructed from past frames. These representat
判断口径 agnes-3.0-flash · 入库 #84 · 回首页