With as few as 12 to 30 liquid neurons, we demonstrated a car autonomously parallel parking, driving, and a drone flying — control tasks normally requiring vastly larger neural networks.
Ramin Hasani recounts early MIT results showing that tiny liquid neural networks — as few as 12 neurons — could autonomously park, drive, or fly a drone, far outperforming what network size would suggest. ✦ AI generated
Ramin Hasani · The Cognitive Revolution · 2026-07-04 · original ↗
starts at this moment · 12:45
“So maybe for starters, how would you tell the kind of broad story of Liquid AI leading up to what you're doing today and what the company's mission is today?”
with 12 neurons with with actually 12 neurons you could you could parallel park autonomously like a car you know like a small car with 19 neurons you could drive a car with with 30 neurons you can fly autonomously like navigating kind of a drone
verbatim transcript · starts at 12:45
12:45you could you could parallel park autonomously like a car you know like a small car with 19 neurons you could drive a car with with 30 neurons you can fly autonomously like navigating kind of a drone you know so and you can get sensory information and process this information with these a little bit more complex and elaborate version of these neural neural dynamics you know which we
13:06called liquid neural networks and liquid for adaptability. We called it liquid liquid time constant neural networks like that was the LTC kind of paper that we we we got out and we coined the name liquid for the fact that the dynamics of these systems are staying flexible even after training you know so the models would be able to react to new type of inputs that they receive and even learn
13:31during back propagation how to be adaptive towards the inputs that you're receiving you know so it actually encoded a little bit more degrees of freedom on flexibility of the learning dynamics of a neural network compared to artificial neural networks compared to other systems that you have seen that form of dynamics actually allowed us to scale this technology into not just you know not just in robotics but also like
13:55applying it to predictive AI in in financial services in medical domain and in many many different places that we applied in like let's say audio modeling you know multimodal video understanding you know like we applied this technology over and over and we saw promise that this technology is actually very very amazing like you know every neuron is much more complex than a normal kind of neural network but but at the same time
14:18like you don't need that many points of computation in order to actually get get to the results that you want. We also saw that the out of distribution performance of these models are extremely good. So and and they they were suited for robotics applications. So I mean we had interactions with with with the United States Air Force. I mean there was like at that time Boeing was
14:37actually hosting my postto at MIT and and and and there we showed that you can actually fly even jets like with these type of neural networks with like a handful of these neurons you know which was very interesting kind of topic to see how far you can push like let's say out of distribution generalization with a handful of like a very very small set of system you know a system that is like