Can you explain how it is much easier if you have a pre-captured map given what they are doing without using any sensors, all you have is perhaps these recent feed forward tokens not actual Geometry.
But a lot of what I work on is my classes giving me less time to open source nowadays, but I have also worked in implementing and mashing new Papers coming out in Robotics. Anyone who wants to talk more should please connect!
Any reason for using a transformer architecture?
You look at https://olmocr.allenai.org/ which does the best handwritten-to-latex in my opinion also does use VLM.
Also maybe xD not use LLMs to generate your HN description.
I am still yet able to find an LLM which can understand it has to look for files and change config after an error, they have no understanding of when to comment things out and work. To be fair it can make websites, algorithms , copy things nicely but that's about it.
Another tool in the box. import pdb is my way still