No video :(

A Big Step for AI: 3D-LLM Unleashes Language Models into the 3D World

Подписаться 61 тыс.

Просмотров 3,1 тыс.

50% 1

References:
►Read the full article: www.louisbouch...
►Project page with video demo: vis-www.cs.uma...
►Code:github.com/UMa...
►Paper: Hong et al., 2023: 3D-LLM, arxiv.org/pdf/...
►Twitter: / whats_ai
►My Newsletter (A new AI application explained weekly to your emails!): www.louisbouch...
►Support me on Patreon: / whatsai
►Join Our AI Discord: / discord
How to start in AI/ML - A Complete Guide:
►www.louisbouch...
Become a member of the RU-vid community, support my work and get a cool Discord role :
/ @whatsai
#ai #3d #llm

Опубликовано:

26 авг 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 7

@gerdschwaderer 7 месяцев назад

What I would like to see is using a set of artificial 3D scans from CAD models, and the corresponding CAD models themselves to create a LLM for automated reverse engineering. I am sure that has to be possible.

@makhalid1999 Год назад

Reminds me of Deepmind's RT-2. These visual-language models (along with action for robotics for RT-2), might just be the new big thing!

@WhatsAI Год назад

Indeed!

@user-wr4yl7tx3w Год назад

Can such a model generalize to 3D of images unseen in the training data?

@DanFrederiksen Год назад

Interesting but as long as the 3D perception is a jittery mess and fails to capture straight lines as straight lines the perception is probably very far from ideal. I'm also dubious about strict boundary box thinking. Not everything can be boundary boxed and it fails to properly grasp relevant aspects. For instance if you box a person, how do you perceive the arm, the collar, a stain, a wrinkle, a posture etc plus temporal aspects. An unsupervised paradigm forming its own model seems to be the way to go.