Arun Natarajan

Today, we're announcing Heaviside, our foundation model for electromagnetism. Trained on tens of millions of designs and over 20 years of proprietary simulation data, Heaviside predicts electromagnetic behavior from geometry in 13ms, which is 800,000x faster than a commercial solver. Heaviside is not a language model, and it’s not a surrogate model. Heaviside marks a new class of foundation model for physics which understands the fundamental relationships between materials, the geometries and the electromagnetic fields they generate. We’re releasing a research preview of Heaviside in Atlas RF Studio, an interactive agentic sandbox where you describe the EM behavior you want and the model generates the physical structure that produces it. @arenaphysica , we believe the implications of this class of model extend well beyond RF, as the frontier of exquisite hardware is electromagnetically-governed: wireless communication, radar, power delivery, high-speed computing, and the interconnects inside every chip on earth. In the months ahead, we’re excited to scale up Heaviside to broader frequency ranges, design spaces, and to support silicon-level designs, and deploy it with our closest partners and collaborators in service of their biggest design challenges. If you’ve read our thesis, this is just Step 2 in our pursuit of electromagnetic superintelligence. Read the full announcement and try Atlas RF Studio…tell us what you think: arenaphysica.com/publications/r…

@MSZeghdar @NatalieFratto @PratapRanade @packyM @arenaphysica Definitely don't want to take away from the innovation and ingenuity in EM over decades. Given the complexity and size of EM design space, we think of this as a part of a human-driven design that lets us explore a large design space than we typically do given time constaints.

@NatalieFratto @PratapRanade @packyM @arenaphysica “No human would have created it that way” is kinda an overstatement, there’s a growing tendency of underestimating creativity and ingenuity that engineers are capable of, and over-reliance on AI is one of the reasons that can severely inhibit the former.

One of these things is not like the other… The other day @PratapRanade brought home 3 RF circuits. Ok “10GHz band pass-filters” he says, to be precise. The first two are human-made, the third is what they’re calling “an alien geometry” 👾 Look how funky it is. That’s the world’s first-ever AI-made RF circuit achieved by the electromagnetism foundation model @arenaphysica. No human would have created it this way. It’s odd, it looks random, but it really works & it might be the future guts inside every satellite, radar, microwave etc one day.

@bmgentile @_i_am_arya The post (arenaphysica.com/publications/r…) shares a lot about the approach and objectives. You can try the design tool here: studio.arenaphysica.com

@_i_am_arya very cool — any information that can be shared related to this? x.com/bmgentile/stat…

@mihuq @_i_am_arya Afraid not, but we have opened up the tool for folks to try - studio.arenaphysica.com/rf to show what is is possible with such models.

@_i_am_arya Is it open source?

@DavidBGrys @_i_am_arya Here's a plot that compares measured, full EM solver and the model for a couple of examples - one a traditional design and one an unconventional design that achieves a bandpass response as well.

@_i_am_arya S21/S11 measurements vs simulation?

@Macrohard2026 @NatalieFratto @PratapRanade @packyM @arenaphysica Interesting question. Here's the measured response. The sharp filtering is not that easy to design in a small area and the model does it in the order of seconds. These are early stages in this design process - interesting to see how the design process and the design evolves.

@NatalieFratto @PratapRanade @packyM @arenaphysica That's awesome, is it better??

@HaumdauchaAmSee @NatalieFratto @PratapRanade @packyM @arenaphysica

@NatalieFratto @PratapRanade @packyM @arenaphysica Charachteristics?

@PrusskyKorabl @NatalieFratto @PratapRanade @packyM @arenaphysica This is the S21 of the third response - the BPF

@NatalieFratto @PratapRanade @packyM @arenaphysica It's bullshit. Show me the S21

@0x440x46 @NatalieFratto @PratapRanade @packyM @arenaphysica It can potentially be smaller for a given performance spec since it uses unconventional geometry - but like @PratapRanade said, it'll be interesting to see what it can achieve long term. We've only explored a small fraction of the design space.

@NatalieFratto @PratapRanade @packyM @arenaphysica What’s the advantage of it? Is it easier to make? Or it’s just equivalent? It looks more complex. So what’s the benefit ?

@KeatonS400 @NatalieFratto @PratapRanade @packyM @arenaphysica Performs quite well, actually - you can see the sharp roll-offs.

@NatalieFratto @PratapRanade @packyM @arenaphysica The Ai made it, but how does it preform?

@LTG1455 @PratapRanade @NatalieFratto @packyM @arenaphysica Yup, there seems to be some sort of coupling structure there.

@PratapRanade @NatalieFratto @packyM @arenaphysica @anrfic Interesting trap characteristics on the low and high sides along with that odd behavior at 18 to 18.5 GHz, almost seems like a resonant coupling to ground there.

@FrostForger @NatalieFratto @PratapRanade @packyM @arenaphysica More on the training model here (arenaphysica.com/publications/r…). Since the model training set includes designs that include randomly generated shapes, it comes up with complex geometries.

@NatalieFratto @PratapRanade @packyM @arenaphysica so those little isolated squares actually calibrate the current? I don't know what i'm looking at but usually stuff is connected.

@PratapRanade @LTG1455 @NatalieFratto @packyM @arenaphysica And the structure generated by the model creates a geometry that we woudn't come up with but it does get a steep roll-off with a sharp transition band from ~6GHz to 7GHz.

@LTG1455 @NatalieFratto @packyM @arenaphysica @anrfic can provide more detail, but here you go

@PratapRanade @LTG1455 @NatalieFratto @packyM @arenaphysica Note that only the third structure in the photo is a filter. The first one is, of course, a transmission line. and the second one is a planar spiral