Here are some of my big questions

- Latent long/short-term memory
- Continual learning on experience (not datasets)
- Exploration and information gathering
- Counterfactual world models from sensors
- Sensory abstraction facilitating reasoning
- Long-horizon planning

Lmk when I can visit you to the mountains!

I miss you, mofos!

Also an artifact of Hollywood.

Congrats!! 💪

Although we don't know how Harmonic Reasoning works, I don't think that it's "just a VLA".

But why this would lead to smoother control? Because “thinking” is done asynchronously and it doesn’t wait to predict an action?

I also assumed so, as the name probably points to that direction, but they don't explain it well. The main selling point for Harmonic Reasoning in the blogspot is that it allows to think before acting.

True, it was early in the morning and Im still quite jet lagged. 😅

The smoothness of their control is much better than what we see in other VLAs. Do you have any idea why this is the case?

Are you planning to share some of your insights/takeaways? It would be super cool!