Comment by NeoInHacker

I'm working on the wolrd model action (WMA) model, which is used to replace Visual Language Action (VLA) model to bridge the physical world with LLM.

Now I've done my basic researching part, but I'm lack of the courage to dive into this topic. After all, it's a really hard work to it.

So I'm just, you know, scrolling the HN and trying to sharpen my brain and get back to the work.