Application of pretrained large language models in embodied artificial intelligence

HIGHLIGHTS

• who: Input2 from the (UNIVERSITY) have published the research: Application of Pretrained Large Language Models in Embodied Artificial Intelligence, in the Journal: (JOURNAL)
• what: A distinctive feature of this work is that experiments were conducted in both virtual environment and on robotic platforms in a realistic environment. The use of such a hint in SayCan improves the performance of the model for tasks involving negation or reasoning. A limitation of this approach is that, as was shown, improvements are demonstrated only for LLMs with more than 100 billions of parameters.
• how: The other . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.