Very excited to be involved with this much needed effort as a senior editor, a new journal focused on natural and artificial minds, please submit your work!

Minds, Machines, and Brains (MMB)@mmb-journal.bsky.social · 3d ago

Hello world! 👋 We’re Minds, Machines, and Brains (MMB) 👤🤖🧠 a new open access journal from @mitpress.bsky.social exploring the principles of intelligence and cognition across natural and artificial minds. Submissions open this Fall! 🔗 direct.mit.edu/mmb

Happening this morning at #CCN poster session C, @zahmb.bsky.social will present ‘Mechanisms of Emergent Analogical Mapping’ 2026.ccneuro.org/poster/?id=p... please check it out if you’re at CCN!

I'll be at CCN next week. Please get in touch if you want to chat about these positions.

I'm recruiting two postdocs (or potentially PhD students) to work on projects at the intersection of cognition, neuroscience, and AI (with a particular emphasis on mechanistic interpretability). Apply here: docs.google.com/forms/d/e/1F... and please share!

So thrilled to be joining the Psychology Department at @columbiauniversity.bsky.social as an assistant prof next summer! I'll be recruiting for PhD/postdoc to start in Autumn 2027, so if you're interested in using computational approaches to studying human cognition please get in touch!

I'm recruiting two postdocs (or potentially PhD students) to work on projects at the intersection of cognition, neuroscience, and AI (with a particular emphasis on mechanistic interpretability). Apply here: docs.google.com/forms/d/e/1F... and please share!

I am *thrilled* to share this review in @currentbiology.bsky.social out today, by yours truly, @myoo.bsky.social, @michalk.bsky.social, Taro Toyoizumi, @tyrellturing.bsky.social, @taylorwwebb.bsky.social, & @hakwan.bsky.social www.sciencedirect.com/science/arti... 🧵👇

Looking to the brain to improve energy efficiency of AI

Modern artificial intelligence (AI) systems have achieved remarkable capabilities, but at an extraordinary energy cost. Training and running large-sca…

sciencedirect.com

New preprint from the lab! “A number simplex in the human medial temporal lobe” led by @hanlin-zhu.bsky.social 🧵 www.biorxiv.org/content/10.6...

A number simplex in the human medial temporal lobe

Humans handle numbers nimbly, suggesting a richer neural manifold structure than the prevalent mental number line model. In populations of medial temporal lobe (MTL) neurons in humans performing two s...

biorxiv.org

The global neuronal workspace (GNW) is currently the best documented neuroscience mechanism by which conscious processing arises in the human brain — and now Anthropic researchers have discovered a similar workspace inside their large language model ! www.anthropic.com/research/glo...

A global workspace in language models

Interpretability research on Claude's internal thoughts.

anthropic.com

I wrote a book! It's called WHY WE ASK WHY, and it's about the human drive to explain, combining psychology, philosophy, and stories. It will be released on October 6, but it's currently available for pre-order from Barnes & Noble at 25% off with code PREORDER25.

RL has taught sequence models to gather context for extrinsic rewards — solving tasks, hitting goals. But what about intrinsic rewards the model builds from its own predictions? Our new paper on curiosity and open-ended in in-context learning explores this question 🧵👇 arxiv.org/abs/2606.19476

Can In-Context Learning Support Intrinsic Curiosity?

Effective machine learning depends not only on how we model data, but also on what data we choose to collect. While large sequence models have revolutionized data modeling, the problem of automated da...

arxiv.org

How do human minds make sense of big, messy problems? 😵‍💫🌀 How do we distill complexity into something simple enough to solve? 🤔💡 We’ll be tackling these questions (and more!) at two workshops on task representations, abstractions, and construals #CogSci2026 #CCN2026 🧵 framing-the-problem.github.io

Framing the Problem — Workshop Series

A workshop series on representation construction in cognitive science and AI. CogSci 2026 (Rio) and CCN 2026 (NYU).

framing-the-problem.github.io

We don’t always know what problems are hard for LLMs. So devs evaluate on tasks HUMANS find hard or on broad benchmarks. What if we could instead anticipate which scenarios a model will fail on—all without evaluating specific input examples? 🧵NEW PAPER by @jenniferlumeng.bsky.social

Very excited to share that my lab will be moving to Princeton (Neuroscience & Psychology) this fall. I'll be recruiting at all levels (more info to come soon), please share / get in touch if you're interested in joining!

1/ Periodic reminder: decodable ≠ causally used. Or, as we put it: Represented Is Not Computed. New paper w/ the excellent Ishita Darade (not on BSky; www.linkedin.com/in/ishita-da...), an undergrad student: arxiv.org/abs/2605.22488 #representation #NeuroAI #neuroscience #interpretability

Represented Is Not Computed: A Causal Test of Candidate Algorithmic Intermediates in a Transformer

Structured prompts require integrating components according to task-relevant relations. How a network implements this integration is often hard to judge in language or vision, where those relations ar...

arxiv.org

🚀 PhD position in #NeuroAI & neurodevelopment 🚀 Co-supervised by Sarah Lippé and myself, to investigate visual processing & cognition abnormalities in children with neurodevelopmental disorders in a neuroAI framework. Full project details and how to apply here: tinyurl.com/kbuyntpn 🧠🤖 📈

Jeee 🐦‍⬛ I am very proud of our joint effort with @sreejan.bsky.social on the project "Reason to Play" LRMs show human-like rule discovery, and their hidden states predict human brain activity during gameplay 10x better than previous methods Interactive demo + paper: botcs.github.io/reason-to-pl...

Reason to Play - Behavioral and Brain Alignment

32 fMRI-scanned humans and 8 frontier open weight LLMs play ARC-AGI like games with no rules given. The reasoning models match the human learning trajectories and their hidden states predict human bra...

botcs.github.io

New paper from the lab! "Plasticity and language in the anaesthetized human hippocampus" www.nature.com/articles/s41...

Plasticity and language in the anaesthetized human hippocampus - Nature

In the hippocampus, complex processing of sensory stimuli occurs even in the unconscious state.

nature.com

Our new study (Debray*, Karami* et al.) explores how the brain encodes basic math concepts (integers, fractions, shapes). Samuel Debray led the 7T fMRI & behavioral work; I led the MEG. @danielavalerio.bsky.social @chrplr.bsky.social @standehaene.bsky.social www.biorxiv.org/content/10.6...

When and how can test-time thinking allow models to use information latent in their training data? What are the benefits and tradeoffs relative to other solutions like synthetic data augmentation? Pleased to share (after a long delay) an exploration of these issues: arxiv.org/abs/2604.01430 thread:

Improving Latent Generalization Using Test-time Compute

Language Models (LMs) exhibit two distinct mechanisms for knowledge acquisition: in-weights learning (i.e., encoding information within the model weights) and in-context learning (ICL). Although these...

arxiv.org

A new Department of Cognitive Science is being created at Bocconi University in Milan, Italy. Here is the call for a cluster hire (for around 10 faculty) in all areas of cognitive science, at both junior and senior levels: www.unibocconi.it/en/faculty-a... Deadline: May 4th, 2026

Excited to give a talk at #Cosyne2026 about my PhD work! We show that RNNs trained on visual search converge on brain-like solutions, producing primate-like behavior and neural representations. Happy to chat if you're at Cosyne! 📅 March 15, 2026 📍 Lisbon, Portugal www.biorxiv.org/content/10.1...

Can large language models *introspect*? In a new paper, @kmahowald.bsky.social and I study the MECHANISM of introspection in big open-source models. tldr: Models detect internal anomalies through DIRECT ACCESS, but don't know what the anomalies are. And they love to guess “apple” 🍎

How do you knock the induction heads out of an LM while preserving its ability to think? Is it even possible? @keremsahin22.bsky.social's work is worth reading if you haven't seen it yet. hapax.baulab.info

What is the relationship between memorization and generalization in AI? Is there a fundamental tradeoff? In infinitefaculty.substack.com/p/memorizati... I’ve reviewed some of the evolving perspectives on memorization & generalization in machine learning, from classic perspectives through LLMs.

Memorization vs. generalization in deep learning: implicit biases, benign overfitting, and more

Or: how I learned to stop worrying and love the memorization

infinitefaculty.substack.com

Very excited for our second workshop on the computational ingredients of reasoning (Feb 24-27), this one focused on mechanisms of reasoning in both AI and the brain. Check out the program to see our amazing lineup of speakers, and please consider attending! ivado.ca/en/events/me...

Mechanistic Basis of Reasoning (in Brains and AI) | IVADO

ivado.ca

Thrilled that my paper is out in the @nature.com. We explored how the brain builds complex tasks by compositionally combining simpler sub-task representations. The brain flexibly performs multiple tasks by dynamically reusing neural subspaces for sensory inputs and motor actions rdcu.be/eRVUk

Building compositional tasks with shared neural subspaces

Nature - The brain can flexibly perform multiple tasks by compositionally combining task-relevant neural representations.

rdcu.be

Excited to announce a new book telling the story of mathematical approaches to studying the mind, from the origins of cognitive science to modern AI! The Laws of Thought will be published in February and is available for pre-order now.

amazing summary of our work on visual symbolic mechanisms bsky.app/profile/this...

Roman Feiman@romanfeiman.bsky.social · 6mo ago