Eric Brachmann (@eric_brachmann)
2024-11-13 | โค๏ธ 192 | ๐ 32
We wrote a text on how we envision the future of visual mapping: https://nianticlabs.com/news/largegeospatialmodel?hl=en
So far, we have trained ~50 million ACE networks. ๐ Together, thatโs 150 trillion parametersโฆ Not bad! But the future lies in going from local small models to a global large model.