Daniel Kunin

postdoc @UCB_MillerInst
PhD @ICMEStanford
creator @SeeingTheory

[Daniel Kunin @KuninDaniel]

For the last few years, a lot of my work has been driven by the feeling that deep learning is not magic — there are principles, mechanisms, and laws waiting to be understood.

This paper is our attempt to say that clearly!

[Jamie Simon @learning_mech]

1/ Deep learning is going to have a scientific theory. We can see the pieces starting to come together, and it's looking a lot like physics!

We're releasing a paper pulling together these emerging threads and giving them a name: learning mechanics.

🔨 https://t.co/92nSIHameW 🔧

[Daniel Kunin @KuninDaniel]

Had a great time visiting @TTIC_Connect last year -- the ideas I presented have progressed quite a bit since then:
- https://t.co/QqZC9EgxgW
- https://t.co/uqvXVOSdfT

[TTIC @TTIC_Connect]

1/4 The Dynamics of Deep Learning. "Trying to understand deep learning...comes down to understanding this interaction of three components that make the deep learning system," said @KuninDaniel, speaking at TTIC in April last year. Video: https://t.co/AI8YnXgys4

[Daniel Kunin @KuninDaniel]

The Miller Fellowship has been an awesome opportunity and Berkeley is a pretty great place to be!

[UCB Miller Institute @UCB_MillerInst]

Scientist @KuninDaniel (MF 25-28) studies learning in neural networks to uncover principles of intelligence in artificial & biological systems. The Miller Fellowship gives me freedom to take risks and grow as a researcher & communicator. Nominate by 9/10: https://t.co/uHTZ7Xm25A

[Alex Atanasov @ABAtanasov]

If you’re a researcher in math or CS wondering what will be left to work on as AI charges through our fields, rest assured: the final theory is still out there waiting for us. It’s not even fully formulated let alone solved. What is the structure and form of thought itself?

[Daniel Kunin @KuninDaniel]

New work by @_AmilDravid, extending his really neat work on Rosetta Neurons through the lens of scaling laws!

A nice example of how mech. interp and learning mechanics can complement one another, bringing different perspectives that together lead to deeper insights

[Amil Dravid @_AmilDravid]

Scaling laws describe how loss changes with scale. Do neurons inside models change predictably too?

We study vision and language models up to 30B params and find systematic scaling in neuron universality, specialization, and selectivity.

Paper+code: https://t.co/1f1mQGnnZ4

1/n

[Adam Shai @adamimos]

A longstanding dream of interp is to decompose activations into distinct, interpretable parts.

But when should we expect that to work, and what even are such parts?

New from Simplex: transformers factor their world into orthogonal subspaces, even when it costs accuracy.🧵👇

[Daniel Kunin @KuninDaniel]

@rzebrahimi @giovannimarchet @AdeleMyersPhD @hopfbifurcator @ninamiolane @rzebrahimi this is a very interesting and related work -- lets chat!

[Daniel Kunin @KuninDaniel]

Excited to share that our paper “Sequential Group Composition: A Window into the Mechanics of Deep Learning” was accepted to ICML 2026 in Seoul!

Co-led with @giovannimarchet
and @AdeleMyersPhD @hopfbifurcator @ninamiolane

Paper: https://t.co/8HsLrKWtlf

[Daniel Kunin @KuninDaniel]

For me, this paper is learning mechanics in action!

Mech interp first identified that NNs use Fourier features in algebraic tasks - great work @bilalchughtai_ @justanotherlaw @NeelNanda5

Learn mech asks why training produced those features, in that order, with that architecture

[Daniel Kunin @KuninDaniel]

Yes — by leveraging associativity.

We explicitly construct efficient solutions: RNNs can compose elements sequentially in k steps, while deep MLPs can compose adjacent pairs in parallel in log k layers

and we find preliminary evidence that GD can discover these solutions!

[Sebastien Bubeck @SebastienBubeck]

From "Mathematical theory of deep learning: Can we do it? Should we do it?" to "There Will Be a Scientific Theory of Deep Learning".

It's respectively the title of a talk I gave four years ago, and the title of an arxiv paper from four days ago.

I really like the "learning mechanics" perspective (think of it as a continuation of "statistical mechanics", "quantum mechanics", and so on). Several of my last academic papers can be viewed under that lens (e.g. Learning threshold neurons via the “edge of stability”; or LEGO). I'm not as optimistic as the authors of the recent arxiv paper that we will EVER be able to reach what the "physics mechanics" field have achieved, but it's certainly worth trying.

Talk: https://t.co/QsBPHP0fDm
Paper: https://t.co/N4JSj3AkYZ

[Daniel Kunin @KuninDaniel]

@scifordl @ZKadkhodaie @FlorentinGuth @learning_mech @AntSclocchi Love the hats!

[Daniel Kunin @KuninDaniel]

@tydsh Yes, agreed. “Learning mechanics” is a scientific program many researchers have been building toward for years; our goal was to clearly state the evidence for such a theory

Your works are great examples of 2.1 (have read many), we should have cited them, adding them now for v2

[Daniel Kunin @KuninDaniel]

@nico_anguita Thanks @nico_anguita!

[Daniel Kunin @KuninDaniel]

For the last few years, a lot of my work has been driven by the feeling that deep learning is not magic — there are principles, mechanisms, and laws waiting to be understood.

This paper is our attempt to say that clearly!

[Jamie Simon @learning_mech]

1/ Deep learning is going to have a scientific theory. We can see the pieces starting to come together, and it's looking a lot like physics!

We're releasing a paper pulling together these emerging threads and giving them a name: learning mechanics.

🔨 https://t.co/92nSIHameW 🔧

[Krzakala Florent @KrzakalaF]

Wir mussen wissen. Wir werden wissen

[Arthur Jacot @ArthurJacot3]

Very happy to be part of this project. We've compiled the main reasons why a Theory of Deep Learning is possible if not inevitable!