« AutoRT » : différence entre les versions
(Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' AutoRT''' == Anglais == ''' AutoRT''' Foundation models that incorporate language, vision, and more recently actions have revolutionized the ability to harness internet scale data to reason about useful tasks. However, one of the key challenges of training embodied foundation models is the lack of data grounded in the physical world. <small> [https://auto-rt.github.io/ Source : github]... ») |
m (Remplacement de texte : « ↵↵<small> » par « ==Sources== ») |
||
| Ligne 10 : | Ligne 10 : | ||
''' AutoRT''' | ''' AutoRT''' | ||
Foundation models that incorporate language, vision, and more recently actions have revolutionized the ability to harness internet scale data to reason about useful tasks. However, one of the key challenges of training embodied foundation models is the lack of data grounded in the physical world. | Foundation models that incorporate language, vision, and more recently actions have revolutionized the ability to harness internet scale data to reason about useful tasks. However, one of the key challenges of training embodied foundation models is the lack of data grounded in the physical world.==Sources== | ||
[https://auto-rt.github.io/ Source : github] | [https://auto-rt.github.io/ Source : github] | ||
Version du 27 janvier 2024 à 15:59
en construction
Définition
XXXXXXXXX
Français
AutoRT
Anglais
AutoRT
Foundation models that incorporate language, vision, and more recently actions have revolutionized the ability to harness internet scale data to reason about useful tasks. However, one of the key challenges of training embodied foundation models is the lack of data grounded in the physical world.==Sources==
