←
Daniel Yamins770 posts
Daniel Yamins avatar

Daniel Yamins

@dyamins

CS, psych, and neuro prof @ Stanford. NeuroAI and "regular AI". Also pianos, harpsichords, pipe organs, and bonsai. danyamins.substack.com

◷ Joined April 2009▧ 47 Photos and videos
Daniel Yamins avatar
Daniel Yamins@dyamins·Nov 13

For years people in NeuroAI have been wondering what the relationship between CNNs and transformers is as brain models, but the ground has been kind of muddy. Now I think we are starting to see underlying situation more clearly. Transformers > CNNs -- in interesting ways!

In neuroscience, a canonical microcircuit is thought to subserve all cortical computation. In AI, neural networks universally subserve intelligent behavior. Is there convergence between computational motifs in natural and artificial intelligence? Work with @dyamins 🧠🤖

Post attachment
Atlas Kazemian avatar
⟳ Daniel Yamins retweeted
Atlas Kazemian@AtlasKazemian·Nov 9

Policy: give PsiBorg a goal image, and it generates robot actions. At the demo, arrange your objects into a goal, take a photo, then reset the scene. Watch the robot work toward it autonomously.

1:25
Daniel Yamins avatar
Daniel Yamins@dyamins·Nov 9

PsiBorg is a pretty amazing robot! It's incredibly rewarding to see one's algorithms come to life (if that's the right phrase?) in a real-world setting. Congrats @AtlasKazemian @KlemenKotar @gia_ancone @wenlong_huang #CoRL2026

Robot Capabilities as Probabilistic Inference over Next Token Prediction We are doing a demo at CoRL debuting PsiBorg: an 8B universally promptable robot model for open-world manipulation! One model works simultaneously as a policy, a simulator, and a progress tracker. It is trained from scratch, developed fully in-house at #Stanford, not a VLA or WAM, and (tries to) work with new objects and new goal images you throw at it! Come try it at #CoRL2026! 🕛 Mon Nov 9 · 12–6:30 PM CST 🕙 Tue Nov 10 · 10 AM–6:30 PM CST 📍 Demo #2 · Lone Star (3rd floor), JW Marriott Austin 🌐 neuroailab.github.io/psi-web…

0:37
Daniel Yamins avatar
Daniel Yamins@dyamins·Nov 4

deep thoughts from @khai_loong_aw, who has a lot of deep thoughts!

What would it take for AI to learn as efficiently as a child? And how close are today's LLMs, world models, and robots? Two targets: pretraining efficiency and zero-shot flexibility. No AI system today has both.

Declan Kutscher avatar
⟳ Daniel Yamins retweeted
Declan Kutscher@kutsch_d·Oct 28

1/ Animals explore without rewards, tasks, or instructions. What computational objective drives that autonomy? We trained virtual flies with intrinsic-motivation algorithms to see which best reproduce real fly behavior and brain activity. Work with @rdkeller and @aran_nayebi !🧵

0:23
Michael C. Frank avatar
⟳ Daniel Yamins retweeted
Michael C. Frank@mcxfrank·Oct 28

How do children learn the meanings of their first words? One idea is cross-situational learning: tracking which words go with which things across many situations. In a new preprint, we test this idea at scale on video from children's own perspective 🧵 arxiv.org/abs/2610.31842

Post attachment
Martin Schrimpf avatar
⟳ Daniel Yamins retweeted
Martin Schrimpf@martin_schrimpf·Oct 28

Super excited to share that I'm co-founding Read/Write Labs for #NeuroAI applications to human brain health and human-aligned AI. We could not ask for a more wonderful team: prn.to/4yK9vqo

Daniel Yamins avatar
Daniel Yamins@dyamins·Oct 27

Streams of thought for natural reasoning in the physical world. *This is PSI-0.6 release* Congrats @khai_loong_aw @KlemenKotar at the PSI team!

Chain-of-thought transformed AI reasoning, but it is limited to words. What's the physical-world analogue? Introducing Ψ-0.6, one model that reasons in *streams of thought*: words, depth, motion, camera pose, and imagined scenes. And it learns when to use which! 🧵

0:51
Precision Neuroscience avatar
⟳ Daniel Yamins retweeted
Precision Neuroscience@PrecisionNeuro_·Oct 14

Introducing the Precision Brain Atlas: high-resolution neural recordings from 70 patients across 12 academic medical centers. A growing resource for studying human neural function- and a step toward a Whole-Brain Interface.

Daniel Yamins avatar
Daniel Yamins@dyamins·Oct 7

People are prophecying the death of math but actually in the last few months is the first time that I have even started thinking about hiring a math PhD as a postdoc, because the prospects of doing advanced math in my area are so much brighter now.

Jiaheng Hu avatar
⟳ Daniel Yamins retweeted
Jiaheng Hu@JiahengHu1·Oct 6

We’ve all seen the cool “Astra for robotics” demos. But behind the scenes? Slow rollouts, hand-engineered APIs, and/or simulated behaviors that struggle on real robots. How do we make coding agent actually work in the physical world? 🦾 Introducing SimEX: Simulation-Integrated Robotics AutoResearch 🧵 arxiv.org/abs/2609.38982

0:36
Apurva Ratan Murty avatar
⟳ Daniel Yamins retweeted
Apurva Ratan Murty@apurvaratan·Oct 6

Another update from our topography work from (high-schooler!) Navneet Prakash. Navneet trained path-integrating RNNs with TopoLoss and found that they recover a much more brain-like center-surround RF connectivity structure than baseline models (w/o any post-hoc sorting)!

Post attachment
Martin Schrimpf avatar
⟳ Daniel Yamins retweeted
Martin Schrimpf@martin_schrimpf·Oct 4

...that was supposed to read "model-brain alignment is now strong enough" 🤦 Posting early morning on the way to the airport took a toll

Martin Schrimpf avatar
⟳ Daniel Yamins retweeted
Martin Schrimpf@martin_schrimpf·Oct 4

Questions in Systems Neuroscience are indeed changing, but to me the new ones are even more exciting! Some years ago, @JamesJDiCarlo showed an old clip of Hans-Lukas Teuber (the founder of @mitbrainandcog: bcs.mit.edu/events/hans-luka…) saying that science goes through stages: explain, predict, control. #NeuroAI first moved us to predict, and I think it's super exciting that we're firmly moving into control: - prediction is pretty well established by now (e.g. Brain-Score.org; algonautsproject.com), although models are not perfect and can fail on simple stimuli (what is missing?) - the field is actually making progress on a theory for why this works (@dyamins & @aran_nayebi arxiv.org/abs/2607.08561, @tyrell_turing nature.com/articles/s41593-0…). - model-synthesized stimuli can neuromodulate visual cortex and the human language network (@PouyaBashivan @KohitijKar science.org/doi/10.1126/scie…, Walker @sinzlab pubmed.ncbi.nlm.nih.gov/3168…, @GretaTuckute nature.com/articles/s41562-0…, and more) - even for invasive techniques, topographic models predict and steer the behavioral effects of microstimulation; optogenetics and muscimol (proceedings.iclr.cc/paper_fi…, biorxiv.org/content/10.1101/…) - and finally model-brain alignment is not strong enough that we can model atypical processing in dyslexia, autism, aphasia, and anhedonia (@melikahnd_1 arxiv.org/abs/2509.24597, pubmed.ncbi.nlm.nih.gov/3570…, arxiv.org/abs/2607.11621, @melikahnd_1 anhedonic-ai.epfl.ch) How processing breaks down, and how we can push it back toward healthy, are very much algorithmic questions about the brain with a clear real-world impact. And now we can actually test them, how cool is that!

I had a feeling recently that seems to be corroborated by chats with colleagues, so I decided to share it here. A lot of systems neuroscientists driven by algorithmic-level questions are going through what looks and feels like a research depression. 🧵 (1/n)

Daniel Yamins avatar
Daniel Yamins@dyamins·Sep 16

Yeah seriously @SakanaAILabs ImageNet or it didn’t happen… my guess is the true state of the art in bioplausible learning surpassed this years ago …

Hmm, these results are only on MNIST, which even trivial methods like Feedback Alignment work well on. Of course, everything works on MNIST! 😉 Which is why we focused on bioplausible learning that scaled w/ backprop on ImageNet 6 years ago... arxiv.org/abs/2003.01513