>But how does LLMs help in making chat bots better, help with this "multi-sensory" data.
All three offerings from the linked blog post are either Vision LLMs or Vision/Action LLMs.
All three offerings from the linked blog post are either Vision LLMs or Vision/Action LLMs.
That does not help a lot.
But your entire premise is wrong regardless of that.
Even if VLAs were forever bound to outputting text, you'd have to prove that they're fundamentally incapable of emitting text that maps to useful action sequences. No proof of that whatsoever - and plenty of empirical evidence suggests otherwise. Even non-specialist LLMs like ChatGPT are getting better at controlling robots and navigating 3D environments, if slowly.
You don't understand what I am saying. The crux of your misunderstanding is here
>emitting text that maps to useful action sequences
If you have a static mapping from text to action, then you are throwing away all the advantage of using an AI. The whole point of AI is that you can get an output from an input without explicit mapping. So If you use explicit mapping anywhere in the chain, then you lose most of the advantage of using the AI.
So if your hardware, physical vocabulary is limited, like move left/right/up/down then what you say could work. But something that have the dexterity of a human form, this vocabulary is nearly infinite. You won't be able to use explicit mapping there.
Your entire premise is wrong.
Modern action decoders are different, and usually take the form of neural networks trained end to end jointly with the rest of the model. Not fundamentally more expressive, just more in line with what we want.
So What is LLM is used here for? It is used for mere translation between different robots. So it is mostly symbolic translation.
What I am talking about is to translation LLM inference directly to movements. For example, if you ask an LLM, how do I open the microwave door? It will list the steps. I am talking about a system that can go from "put the thing in the microwave", to action steps, without having to never once demonstrate it physically, and do it just from LLM inference.
In short, the way LLMs used here is not (categorically) the way I was asking about.
https://arxiv.org/pdf/2505.23705
https://www.pi.website/download/pistar06.pdf
https://www.pi.website/download/pi07.pdf
The thing literally has a diffusion "action expert" sit in the same attention system as a pre-trained VLM. And the VLM itself is ALSO trained to generate raw actions as a part of the training recipe (the first paper) - it just doesn't do it at inference time. What the "action expert" does is parallelize the action generation process - based on VLM's internal states.
It's exactly the thing you claimed to be impossible. Described in detail in a paper from 2025. What's your excuse?
You already downgraded your claims from "LLMs are irrelevant to robotics" to a measly "you can't train a useful robotics LLM because there's not enough data". And you say that while looking at an LLM that was pre-trained on all of internet scraped and only then reused for robotics.
Both the pool of robotics-relevant data and the performance of foundation model LLMs grow over time. All the companies that are serious about robotics are serious about scaling up data collection.
I'm not going to claim that this "LLM core" approach is the best approach to AI robotics possible - but if you're betting on it failing outright, you're going to be fighting uphill.
This was the claim from the very beginning. You should have asked why I think what I think, instead of leading with "the entire premise is wrong!"...
Your entire premise was wrong at every point, and now you're trying to wriggle your way out of admitting it.
Prove it!
Read the command line prompt: --task="pick up the red cube"
So it should be something like, "put back this slipped cycle chain back on sprocket"..
Read the command line prompt: --task="pick up the red cube"
There is a gif directly below it.
This is a completely open source model and arm you can replicate yourself.
This isn't true.
Obviously there is a lot of variety in architecture, but in the prototypical example there are vision and languages encoders and an action decoder which decodes direction into action steps. Eg, Hugging Face SmolVLA:
> Specifically, the VLM processes sensorimotor states, including images from multiple RGB cameras, and a language instruction describing the task. In turn, the VLM outputs features directly fed to the action expert, which outputs the final 3 continuous actions.[1]
Or NVidia's GR00T N1:
> A diffusion transformer (DiT) processes the robot’s proprioceptive state and action, which are then cross-attended with image and text tokens from the Eagle-2 VLM backbone to output the denoised motor actions.[2]
(Emphasis mine)