Re:Fei-Fei Li: Spatial Intelligence Is the Next Frontier in ...
by sega_sai on Thursday July 03, 2025 @03:02PM
(#44458175)
I feel that if words/phrases/whole texts can be embedded well in high dimensional spaces as points, the same must apply to the 3d world. I'm sure there will be embeddings of it (i.e. mapping the 3-d scene into a high-D vector) and then we'll be work with those embeddings as LLMs work with text (disclaimer: I am not an expert in the field ).
[ Parent
| on HN ]
There are no comments on this comment yet.