LLMs like ChatGPT are based on Transformer AI models introduced 2017. Transformer was later also applied for computer vision with the introduction of self-supervised Vision Transformers.

If you want to know how ViTs work and what the uses cases are 👉 https://www.reply.com/en/artificial-intelligence/vision-transformers

#LLM #Chatgpt #gpt #AI #deeplearning #visiontransformer #computervision #CV

Big news in #EmbodiedAI by Meta! 🤯

VC-1 is an #AI visual cortex supporting sensorimotor skills, trained on the new Ego4D, it outperforms best-known results.

Adaptive Skill Coordination (ASC) achieves near-perfect performance on long-horizon tasks! 🤖

Of course we at Reply are already working on this with our fleet of robots. 😁

https://ai.facebook.com/blog/robots-learning-video-simulation-artificial-visual-cortex-vc-1/

#AI #deeplearning #computervision #AMR #robotics #robot #ML #visiontransformer #embodiment