Gordon Wetzstein (@GordonWetzstein)
2025-06-06 | โค๏ธ 452 | ๐ 53
The context size of video world models is only a few frames. Like a human with severe memory loss! We design a long-term memory for world models based on explicit 3D representations inspired by the human mind. This enables long-term consistency. https://spmem.github.io/ 1/3 https://x.com/GordonWetzstein/status/1930984909755359476/video/1
๋ฏธ๋์ด
