Загрузка видео...

Не удалось загрузить видео

На главную

Introducing LDA, a latent world action foundation model that, for the first time, unifies the utilization of heterogeneous embodied data across simulation and reality, humans and robots, and varying levels of action quality and annotation. By breaking long-standing data silos in embodied intelligence, LDA enables the field, much like...

40,883 просмотров • 6 месяцев назад •via X (Twitter)

Комментарии: 5

Фото профиля Jiangran Lyu
Jiangran Lyu6 месяцев назад

We have open-sourced the model and code! Project Page: arXiv:

Фото профиля Sharpa
Sharpa6 месяцев назад

Nothing better than Sharpa hands to cook a burger just right! Joke aside, it's great to see the ecosystem coming up with new recipes to scale robot learning👍

Фото профиля abdel
abdel6 месяцев назад

oh no why do you release it now.. i just finished my essay on world models haha and I am not sure yet in which category your world model would fit in. seems exciting, great job.

Фото профиля Tradeye
Tradeye6 месяцев назад

LDA just dropped the mic @GalbotRobotics 🔥 Unifying sim + real, human + robot data? Absolute game changer! Tradeye is out here supplying the messy real-world chaos you need: narrated POV video from licensed HVAC/plumbing/electrical crews in actual tight attics, crawlspaces & lived-in homes (C20 licensed of course). DM me if you want some authentic trades data to supercharge the model? Let’s make robots unstoppable together 🚀

Фото профиля Akito
Akito6 месяцев назад

Can consumers-captured video serve as training data for the model??

Похожие видео