This very nice paper provides some useful pushback against PRH. To me science is like a damped pendulum, where we need to swing back and forth a few times before converging on truth. So don't worry PRH fans, I'll be trying to swing us back out of the cave again soon!

A. Sophia Koepke@askoepke.bsky.social · 5mo ago

New paper: Back into Plato’s Cave Are vision and language models converging to the same representation of reality? The Platonic Representation Hypothesis says yes. BUT we find the evidence for this is more fragile than it looks. Project page: akoepke.github.io/cave_umwelten/ 1/9

Sharing “Neural Thickets”. We find: In large models, the neighborhood around pretrained weights can become dense with task-improving solutions. In this regime, post-training can be easy; even random guessing works Paper: arxiv.org/abs/2603.12228 Web: thickets.mit.edu 1/

The AI discourse sometimes seems to center on "Is AI good or is it bad?" I find this framing unproductive. AI is not a fixed thing. I would prefer to ask "How might we use this technology for good, and mitigate the bad?" What a shame if the best use we can come up with is no use at all.

Today we present a new framework for measuring human-like general intelligence in machines: studying how and how well they play and learn to play all conceivable human games compared to humans. We then propose the AI Gamestore a way to sample from popular human games to evaluate AI models.

Our grad-level "Deep Learning" course (MIT's 6.7960) is now freely available online through OpenCourseWare: ocw.mit.edu/courses/6-79... Lecture videos, psets, and readings are all provided. Had a lot of fun teaching this with @sarameghanbeery.bsky.social and @jeremybernste.in!

Super accessible write up on what we and others have been up to on representational convergence in AI models, and the platonic representation hypothesis, along with contrary views. I'm a big fan of Quanta Magazine, so it was very cool to see them cover this!

Ben Brubaker@benbenbrubaker.bsky.social · 8mo ago

New story by me in @quantamagazine.bsky.social unpacking the provocatively named "Platonic representation hypothesis." In what sense, and to what degree, are different AI models are growing more similar?

Impromptu NeurIPS meetup: "representational convergence by the beach." We will meet at ballroom 20c (near lunch) 2pm Fri and walk over to Marina. Will chat about platonic reps, fractured reps, or anything else about where all these models are heading. Anyone is welcome to join!

Join us TODAY for the 3rd Perception Test Challenge perception-test-challenge.github.io @iccv.bsky.social Ballroom B, Full day Amazing lineup of speakers: Ali Farhadi, @alisongopnik.bsky.social, Phlipp Krahenbul, @phillipisola.bsky.social

Over the past year, my lab has been working on fleshing out theory + applications of the Platonic Representation Hypothesis. Today I want to share two new works on this topic: Eliciting higher alignment: arxiv.org/abs/2510.02425 Unpaired learning of unified reps: arxiv.org/abs/2510.08492 1/9

Interesting reaction from ChatGPT to the HHS mRNA memo. It finds it so implausible that it thinks it's fake. From the perspective of a ~2024(?) trained model, 2025 policies are so absurd as to be unbelievable... chatgpt.com/share/689364...

#CVPR2025 provided coaching for all orals. Do you think the talks were improved compared to last year? * Better than last year * About the same * Worse than last year Share your thoughts in the thread!

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!

Foundations of Computer Vision

The print version was published by

visionbook.mit.edu

Behind every great conference is a team of dedicated reviewers. Congratulations to this year’s #CVPR2025 Outstanding Reviewers! cvpr.thecvf.com/Conferences/...

PINEAPPLE, LIGHT, HAPPY, AVALANCHE, BURDEN Some of these words are consistently remembered better than others. Why is that? In our paper, just published in J. Exp. Psychol., we provide a simple Bayesian account and show that it explains >80% of variance in word memorability: tinyurl.com/yf3md5aj

Lots of different definitions of reasoning floating around. How about this? Reasoning is planning in knowledge space. Planning = find a sequence of actions that achieves a goal. Reasoning = find a sequence of inferences that answers a query. Then it's no surprise that RL can amortize both.

Something I don't quite understand: deepseek showed that each gpu is more valuable than we thought. You can do more with fewer. So why did chip stocks crash? Is it because people assume that AI demand will satiate at a certain level of intelligence? Or is there some other explanation

When I was a kid I was fascinated by SETI, the Search for Extraterrestrial Intellitence. Now we live in an era when it is becoming meaningful to search for "extraterrestrial life" not just in our universe but in simulated universes as well. This project provides new tools toward that dream:

Sakana AI@sakanaai.bsky.social · 2y ago

Introducing ASAL: Automating the Search for Artificial Life with Foundation Models Blog: sakana.ai/asal/ We propose a new method called Automated Search for Artificial Life (ASAL) which uses foundation models to automate the discovery of the most interesting and open-ended artificial lifeforms!

Personal vision tasks–like detecting *your mug*--are hard; they’re data scarce and fine-grained. In our new paper, we show you can adapt general-purpose vision models to these tasks from just three photos! 📝: arxiv.org/abs/2412.16156 💻: github.com/ssundaram21/... (1/n)

At NeurIPS this year my lab is sharing a few papers and talks. They are all about the following question: how to characterize the geometry of deep learning problems, and in particular how to measure *distance*? Each paper/talk gives a rather different answer, detailed below:

Making a lecture on inference methods for deep nets. Here is my attempt at mapping out the interplay between training and inference. A few items I wasn't sure where to put. You could break it down differently. What did I get wrong?

Sharing some new work! A big dream in AI is to create world models of sufficient quality that you can train agents within them. Classic simulators lack visual diversity and realism. GenAI lacks physical accuracy. But combining the two can work pretty well! Paper: arxiv.org/abs/2411.00083

I think I will start posting about research, and maybe other thoughts, here. Hope we can get a critical mass like there was on science Twitter!