🔥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

If two models are more similar to each other than a third on ImageNet, will this hold for medical/ satellite images? Our preprint analyzes how vision model similarities generalize across datasets, the factors that influence them, and their link to downstream task behavior. 🧵1/7

New (short) paper investigating how the in-context inductive biases of vision-language models — the way that they generalize concepts learned in context — depend on the modality and phrasing! 1/4

#Anonymous: Trump and Elon are going to destroy your democracy, this has been planned.

I encourage all of my friends and fellow scientists in the US to go outside and march against Trump’s and Elon’s oligarchy. There’s nothing at this point that is more important than fighting for democracy! Democracy is in real danger and we here in Europa are concerned.

New preprint! In “Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior” we synthesize AI and cognitive science works into a perspective on pursuing generalizable understanding of cognition. Thread:

I think Elon Musk should be expelled from the British Royal Society. Not because he peddles conspiracy theories and makes Nazi salutes, but because of the huge damage he is doing to scientific institutions in the US. Now let's see if he really believes in free speech.

Alex Cole Since WWII, Democrats have outperformed Republicans on the economy. GDP growth averages 4.23% under Dems vs. 2.36% under GOP. Job creation? 1.7% yearly for Dems, 1.0% for Republicans. Also, 9 of the last 10 recessions started under Republican presidents. Data speaks louder than

Excited to share that our paper "Bridging the human–AI knowledge gap through concept discovery and transfer in AlphaZero" is now out in PNAS! With Nenad Tomasev, Tom McGrath, Demis Hassabis, Ulrich Paquet, Been Kim 🎉 📄 doi.org/10.1073/pnas.2…

Here’s an extended version of my PhD defense talk about our work on *representational alignment between humans 🧠 and machines 🤖 for computer vision* that I gave two weeks ago MPI für Kognitions- & Neurowissenschaften cbs.mpg.de/cbs-coconut/lu…

“No government—regardless of which party is in power—should dictate what private universities can teach, whom they can admit and hire, and which areas of study and inquiry they can pursue.” - President Alan Garber hrvd.me/GarberRespond3…

Here's a nice "proof without words": The sum of the squares of several positive values can never be bigger than the square of their sum. This picture helps make sense of how ℓ₁ and ℓ₂ norms regularize and sparsify solutions (resp.). [1/n]

🔄✨ Come join us at the Second edition of the Re-Align workshop ICLR 2025! 🚀🧠 The workshop explores the fascinating question of how artificial and biological systems align in their representations of the world. #ReAlign #ICLR2025

Leo Dianbo Liu Martin Schrimpf Alex Williams brian 🤔 Curious about what "representational alignment" actually means? 🧩 Check out our freshly updated preprint! 📝✨ We've incorporated exciting findings and contributions from the previous edition into this comprehensive update! x.com/sucholutsky/st…

How do language models generalize from information they learn in-context vs. via finetuning? We show that in-context learning can generalize more flexibly, illustrating key differences in the inductive biases of these modes of learning — and ways to improve finetuning. Thread: 1/

Beautiful work by Andrew Lampinen and Stephanie Chan as ever

Joe 🇵🇸🕎 Hideous Dispropaganda Elon Musk might have intentionally mischaracterized the AfD as centrist for several reasons. 1. Political alignment: He may share AfD's Eurosceptic and anti-immigration views, aiming to legitimize them. 2. Influencing public opinion: His high-profile status could normalize