๐Ÿ“š ์„ธํ˜„'s Vault

๐ŸŒ ๋„๋ฉ”์ธ

  • ๐Ÿ”ฎ3D-Vision
  • ๐ŸŽจRendering
  • ๐Ÿค–Robotics
  • ๐Ÿง LLM
  • ๐Ÿ‘๏ธVLM
  • ๐ŸŽฌGenAI
  • ๐ŸฅฝXR
  • ๐ŸŽฎSimulation
  • ๐Ÿ› ๏ธDev-Tools
  • ๐Ÿ’ฐCrypto
  • ๐Ÿ“ˆFinance
  • ๐Ÿ“‹Productivity
  • ๐Ÿ“ฆ๊ธฐํƒ€

๐Ÿ“„ Papers

  • ๐Ÿ“š์ „์ฒด ๋…ผ๋ฌธ172
Home

โฏ

bookmarks

โฏ

we wrote a text on how we envision the future of visual mapping so far we have t

we-wrote-a-text-on-how-we-envision-the-future-of-visual-mapping-so-far-we-have-t

2024๋…„ 11์›” 13์ผ1 min read

  • ๊ธฐํƒ€

Eric Brachmann (@eric_brachmann)

2024-11-13 | โค๏ธ 192 | ๐Ÿ” 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. ๐Ÿ˜Ž Together, thatโ€™s 150 trillion parametersโ€ฆ Not bad! But the future lies in going from local small models to a global large model.


Tags

domain-๊ธฐํƒ€


๊ทธ๋ž˜ํ”„ ๋ทฐ

  • Eric Brachmann (@eric_brachmann)
  • Tags

๋ฐฑ๋งํฌ

  • domain-๊ธฐํƒ€

Created with Quartz v4.5.2 ยฉ 2026

  • GitHub
  • Sehyeon Park