[person4268]

It's pretty impressive, just note (emphasis added):

> At Liquid AI, we take an open-science approach. We have and will continue to contribute to the advancement of the AI field by openly publishing our findings and methods through scientific and technical reports. As part of this commitment, we will release relevant data and models produced by our research efforts to the wider AI community. We have dedicated a lot of time and resources to developing these architectures, *so we're not open-sourcing our models at the moment*. This allows us to continue building on our progress and maintain our edge in the competitive AI landscape.

Looks like there's no paper (or similar) yet, either. Hopefully they'll release a more detailed writeup soon.

[programjames]

The ideas come from these papers:

1. [Liquid Time-Constant Networks (2020)](https://arxiv.org/abs/2006.04439)

This is essentially a neural ODE applied to leaky integrate-and-fire.

2. [Closed-form Continuous-time (2022)](https://arxiv.org/abs/2106.13898)

A closed-form approximation of the first.

[a_wild_dandan]

More citations from their blog[1] too.

[1] https://www.liquid.ai/blog/liquid-neural-networks-research

[turnsout]

Missed opportunity. I would argue that the only way they CAN make these smaller models competitive is to make them openly available. As a developer, I'm not going to choose an unknown startup's model over bigger closed models from OpenAI or Anthropic. And if I really need something smaller and faster, I'd prefer to run the model myself for better control and no risk of the model being "upgraded."

[swyx]

this is the "paper": a list of citations https://www.liquid.ai/blog/liquid-neural-networks-research

i guess they're not really making an effort to explain how specifically all this comes together to create LFMs.

other finds https://x.com/swyx/status/1840794198913794236