And come see the substack series: danyamins.substack.com/p/the-theory...

The Theory of Contravariance, Part 0

Breaking down our extensive new theory paper.

danyamins.substack.com

Aran Nayebi@anayebi.bsky.social · 3w ago

1/6 Why have deep neural networks aligned so strongly with brains for the past 15 years? What explains it? @dyamins.bsky.social & I make progress on this question in our new paper👇 In a nutshell, we *prove* that for sufficiently hard tasks, the choice of alignment metric does *not* matter.

Come by our ICLR poster: Session 6, Pavilion 4, Sat 3:15 PM. Unified 3D Scene Understanding Through Physical World Modeling. It's pretty amazing what PSI can get from "just pixels"... Paper: openreview.net/forum?id=NQq... Project: neuroailab.github.io/3wm_page/ Code: github.com/lee-wanhee/3WM

I think we finally made really significant progress on the biggest unsolved "developmental AI" problem: learning from human-scale data. Key idea: zero-shot world models that support concept extraction via approximate causal inference. amazing collab w/ @mcxfrank.bsky.social @khaiaw.bsky.social

Khai Loong Aw@khaiaw.bsky.social · 4mo ago

Children exhibit visual understanding from limited experience, orders of magnitude less than our best models. We introduce the Zero-shot World Model (ZWM). Trained on a single child's visual experience, BabyZWM rapidly generates competence across diverse benchmarks with no task-specific training. 🧵

Hear @dyamins.bsky.social and yours truly discuss causality and ml: x.com/kordinglab/s..., www.youtube.com/watch?v=R-54...

Here is our best thinking about how to make world models. I would apologize for it being a massive 40-page behemoth, but it's worth reading. arxiv.org/pdf/2509.09737

Lots of people are pinging me re PhD applications lately, here is what I tell them. I accept PhD students through: (1) CS (tinyurl.com/4azymrbu Comp Cog Neuro track), (2) Psychology tinyurl.com/4v7793tz and (3) Neuro tinyurl.com/ycx658h9. Good luck!

Hey come to our workshop if you're at CCN this year! neuroailab.github.io/modeling-the...

This looks like it will be fun data-brain-mind.github.io Neurips '25

It was a steep climb in the "early days" (~2012) up the ImageNet gradient towards better visual system models. That tapped out ~2015 after resnet ... But now w/ video models starting to perform, we can push forward again. Task-driven brain models ftw. amazing... @mschrimpf.bsky.social

Yingtian (David) Tang@davidtyt.bsky.social · last yr.

🧠 NEW PREPRINT Many-Two-One: Diverse Representations Across Visual Pathways Emerge from A Single Objective www.biorxiv.org/content/10.1...

🚀 New Open-Source Release! PyTorchTNN 🚀 A PyTorch library for biologically-inspired temporal neural nets: unrolling computation through time. Integrates with our recent Encoder-Attender-Decoder, which flexibly combines models (Transformer, SSM, RNN) since no single one fits all sequence tasks. 🧵👇

Do science folks basically post the same thing here as on Twitter?? Is that the best practice? (I feel very underpowered/ underprepared) when it comes to science social media.

Going to #Cosyne2025? Join us (w/ @mdiamantaki.bsky.social) for our exciting workshop Object-centric Neuronal Representations toliaslab.org/workshop/cos... Featuring diverse species💁‍♀️🐒🐁🐝🕷️🤖 Our goal: Discuss universal & species-specific principles of object-centric vision See you in Montreal🥳

Only 4 days to go until our workshop!! 🪰🐁🤖 If you're at COSYNE, don't miss out on incredible talks and inspiring panel discussions at "Agent-Based Models in Neuroscience: Complex Planning, Embodiment, and Beyond" on March 31 :) Check out the latest schedule: neuro-agent-models.github.io