🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

1/ 🧵👇 What should count as a good model of intelligence? AI is advancing rapidly, but how do we know if it captures intelligence in a scientifically meaningful way? We propose the *NeuroAI Turing Test*—a benchmark that evaluates models based on both behavior and internal

#TalkTuesday - Language may be a defining characteristic of our species, but Ev (like in 'evidence', not Eve) Fedorenko 🇺🇦 provides compelling evidence that it's not required for complex thought.MIT Brain and Cognitive Sciences 🗣️ Watch the MIT Science talk here: youtu.be/woF3jjIupDU?si…

Come to our CCN workshop! Blending iophysical constraints and neural networks. Topographical ANNs + and much more. Meenakshi Khosla talia konkle pouya bashivan Nick Blauch Tim Kietzmann Laura Gwilliams Apurva Ratan Murty Jakob Macke Pieter Roelfsema Martin Schrimpf Andrew Miri Nabil Imam

Tomorrow at Frontiers in NeuroAI symposium Kempner Institute at Harvard University, I will be presenting a poster entitled "A Model of Continuous Phoneme Recognition Reveals the Role of Context in Human Speech Perception" (Poster #17). Work done with Josh McDermott #NeuroAI2025 🧵1/4

Our first NeuroAgent! 🐟🧠 Excited to share new work led by the talented Reece Keller, showing how autonomous behavior and whole-brain dynamics emerge naturally from intrinsic curiosity grounded in world models and memory. Some highlights: - Developed a novel intrinsic drive

I wrote a note on linear transformations and symbols that traces a common conversation/interview I've had with students. Outer products, matrix rank, eigenvectors, linear RNNs -- the topics are really neat, and lead to great discussions of intuitions. cs.columbia.edu/~johnhew//fun-…

Can we precisely and noninvasively modulate deep brain activity just by riding the natural visual feed? 👁️🧠 In our new preprint, we use brain models to craft subtle image changes that steer deep neural populations in primate IT cortex. Just pixels. 📝arxiv.org/abs/2506.05633

🚨Excited to share our latest work published at Interspeech 2025: “Brain-tuned Speech Models Better Reflect Speech Processing Stages in the Brain”! 🧠🎧 arxiv.org/abs/2506.03832 W/ Mariya Toneva We fine-tuned speech models directly with brain fMRI data, making them more brain-like.🧵

Super stoked for our Minds in the Making workshop at @cogscisociety.bsky.social 2025! If you are at all interested in the intersection between cognitive science and design, you won’t want to miss it!! 🧠🛠️

ACL paper alert! What structure is lost when using linearizing attribution like Shapley? We show the nonlinear interactions between features reflect structures described by the sciences of syntax, semantics, and phonology.

Our computer vision textbook is now available for free online here: visionbook.mit.edu We are working on adding some interactive components like search and (beta) integration with LLMs. Hope this is useful and feel free to submit Github issues to help us improve the text!

🚨New Preprint!! Thrilled to share with you our latest work: “Mixture of Cognitive Reasoners”, a modular transformer architecture inspired by the brain’s functional networks: language, logic, social reasoning, and world knowledge. 1/ 🧵👇

The Kempner Institute congratulates its research fellows Isabel Papadimitriou (Isabel Papadimitriou) and Jenn Hu (Jennifer Hu) for their faculty appointments (UBC Linguistics & JHU Cognitive Science) and celebrates their innovative research. Read more here: bit.ly/448heBy #AI #LLMs

I'm hiring at least one post-doc! We're interested in creating language models that process language more like humans than mainstream LLMs do, through architectural modifications and interpretability-style steering.

Out today in nature: we show that individual neurons have diverse tuning to a decision variable computed by the entire population, revealing a unifying geometric principle for the encoding of sensory and dynamic cognitive variables. nature.com/articles/s4158…

Have you heard about our shared task? 📢 Mechanistic Interpretability (MI) is quickly advancing, but comparing methods remains a challenge. This year, as a part of #BlackboxNLP at EMNLP 2025, we're introducing a shared task to rigorously evaluate MI methods in LMs 🧵

Humans and animals can rapidly learn in new environments. What computations support this? We study the mechanisms of in-context reinforcement learning in transformers, and propose how episodic memory can support rapid learning. Work w/ Kanaka Rajan: arxiv.org/abs/2506.19686

🚨New paper! We know models learn distinct in-context learning strategies, but *why*? Why generalize instead of memorize to lower loss? And why is generalization transient? Our work explains this & *predicts Transformer behavior throughout training* without its weights! 🧵 1/

It’s like chain-of-thought for humans!

🧵 What if two images have the same local parts but represent different global shapes purely through part arrangement? Humans can spot the difference instantly! The question is can vision models do the same? 1/15