Imran Thobani

1/x Our new method, the Inter-Animal Transform Class (IATC), is a principled way to compare neural network models to the brain. It's the first to ensure both accurate brain activity predictions and specific identification of neural mechanisms. Preprint: arxiv.org/abs/2510.02523

I don't see why prediction has to be framed as necessarily at odds with "understanding". The two naturally go hand-in-hand. Prediction is the *minimal* scientific prereq for anything you want to further investigate. We didn't even have successfully predictive systems of large-scale neural population responses in the neurosciences until ML started working. Furthermore, "understanding" isn't an objective measure -- it's aesthetically in the eye of the beholder. So it's not clear there's a well-defined global notion here to begin with, besides prediction alone. If you ask 10 scientists what they mean by "understanding", you'll get > 10 different answers 🙂 Not to mention, causal manipulations are naturally supported in ANNs because they're mechanistic models by construction: you have the entire network graph available to you to perturb as you choose. As the saying goes: “Everything should be as simple as it can be, but not simpler.” And it's quite clear there isn't anything simpler than ANNs without losing tons of predictive power. Why bother "understanding" a system that doesn't even predict the scientific phenomenon at hand?

Super excited to share that my Master’s project, “Convolutional architectures are cortex-aligned de novo,” has been published in Nature Machine Intelligence! nature.com/articles/s4225… w/ @EricElmoznino @michaelfbonner

@locross Thanks, Logan!

@cogphilosopher Great work Imran!!

1/x Our new method, the Inter-Animal Transform Class (IATC), is a principled way to compare neural network models to the brain. It's the first to ensure both accurate brain activity predictions and specific identification of neural mechanisms. Preprint: arxiv.org/abs/2510.02523

@AllenInstitute @jvrsgsty @aran_nayebi @_jacobprince_ @luosha @dyamins 11/X Check out the full paper here: arxiv.org/abs/2510.02523

@AllenInstitute 10/X Overall, our work provides a principled framework for evaluating brain models, improving on previous approaches and contextualizing prior findings. A huge thanks to my incredible co-authors on this work! @jvrsgsty @aran_nayebi @_jacobprince_ @luosha @dyamins

@AllenInstitute @jvrsgsty @aran_nayebi @_jacobprince @luosha @dyamins 11/X Check out the full paper here: arxiv.org/abs/2510.02523

1/ A good world model should be promptable like an LLM, offering flexible control and zero-shot answers to many questions. Language models have benefited greatly from this fact, but it's been slow to come to vision. We introduce PSI: a path to truly interactive visual world models 🧵

Sunrise over Prague

Devoured these pastries from the oldest bakery in Copenhagen today, Skt. Peders Bageri.

AI models segment scenes based on how things appear, but babies segment based on what moves together. We utilize a visual world model that our lab has been developing, to capture this concept — and what's cool is that it beats SOTA models on zero-shot segmentation and physical manipulation tasks. So is segmentation solved, or are we only beginning to learn how to define it in a way that supports downstream applications? Find out how causal probes on world models help address this definitional challenge. Check out our preprint on “Discovering and Using Spelke segments”: neuroailab.github.io/spelke_net Get ready for 🤿 1/n