developmental embodiedment 😎 #DevelopmentalEmbodiedment #GrowAI

‼️ Video models start to reason, let's build-in-public scaled eval together 🚀 github.com/hokindeng/VM... (Apache 2.0) offers 1⃣One-click inference across ALL available models 2⃣Unified API & datasets & auto resume + error handling + eval 3⃣Plug new models and tasks in <5 lines of code a thread (1/n)

Excited to share my essay with @carrot0817.bsky.social, Kaia Gao on the representational substrate of world-reasoning in both humans and machines has been accepted to the SpaVLE Workshop at #NeurIPS2025✨ a thread (1/n)

Very cool work !

best Halloween costume this year

Josh Tenenbaum's inspiring keynote at #cogsci2025 on growing vs scaling AI, the big questions of cognitive science, and the many open questions for the field.

this was a hilarious final slide that just hung up there during q&a

Susan Carey mic-drop at #cogsci2025. "There are no innate concepts: Discuss"

#CoreCognition #LLM #multimodal #GrowAI We spent 3 years to curate 1503 classic experiments spanning 12 core concepts in human cognitive development and evaluated on 230 MLLMs with 11 different prompts for 5 times to get over 3.8 millions inference data points. A thread (1/n) - #ICML2025 ✅

What is the best testbed for human-like cognition in machines?🤔 Hardly anything comes better than gaze understanding. Humans are extremely good at gaze reading 👁️ , and this ability develops extremely early in childhood. Here, we tested 111 VLMs and 65 humans ⬇️

Beautiful to see this initiative from a group of like minded PhD students collaborating together! 🚀

New Paper Alert ‼️ Current VLMs completely fail human gaze understanding 🙀 and scaling does NO help ‼️ However, humans, since an extremely age 🧒, are extremely sensitive to other people's gaze 🙄 👀 No mentors, no labs, only pre-doc students, 111 VLMs, and we did it 😎

I think there is a fundamental division between “physical reasoning” and “intuitive physical reasoning” in human mind. The former is grounded by System 2 where the latter is actually System 1. The physics/graphics I have never thought of - and never thought about this in context of aphantasia

It's an interesting phenomenon that some of the deepest questions about how life works have become what looks like impossibly obscure molecular biology stuck right at the back of Nature, which will never get covered by the science media. Like this. /1 www.nature.com/articles/s41...

Doing research not in your previous areas comes at a cost. Good paper but I disagree on the corollary. Instead, the best scientists should always walk out their comfort zones. And indeed they always do. www.nature.com/articles/s41...

Check out our new work on making robots process touch more like brains! Surprisingly, ConvRNNs best matched mouse cortex—passing the NeuroAI Turing Test. We also developed tactile-specific SSL augmentations and an Encoder-Attender-Decoder framework unifying ConvRNNs, SSMs & Transformers.

This is such a beautiful and important work. I have been thinking about the increasing automation due to AI a lot. Aran here puts into actions and give us such a beautiful work! It’s definitely part of the duties us as scientists to think about these important societal issues.

Sam is 100% correct on this. Indeed, human babies have essential cognitive priors such as permanence, continuity, and boundary of objects, 3D Euclidean understanding of space, etc. We spent 2 years to systematically to examine and show the lack of such in MLLMs: arxiv.org/abs/2410.10855

Sharing a new paper from the lab. This paper, led by Sangyoon Ko, represents a merging of two longstanding research themes in the lab-- adult neurogenesis and systems consolidation. rdcu.be/el18q A short thread follows for those interested. 1/n

Hippocampal reactivation of planned trajectories is required for effective goal choice in an allocentric memory task https://www.biorxiv.org/content/10.1101/2025.05.10.653115v1

If I had more free time, I would become a sci-fi novelist. I have a long list of plots that I want to write. Here's one.

Lovely work — and yet another proof that perceptual integration, likely based on recurrent connections, can occur without awareness during the attentional blink. See also www.pnas.org/doi/full/10....

Loving the new ICLR blogpost track. Here's a cool one on engrams in neuroscience vs mechanistic interpretability: d2jud02ci9yv69.cloudfront.net/2025-04-28-e...

Finally finish making our website 💐 growing-ai-like-a-child.github.io 🤩 with @carrot0817.bsky.social @marstin.bsky.social @tonyfeng.bsky.social @zoryzhang.bsky.social and many others @growai.bsky.social🚶‍♂️🚶‍♀️🚶

#ICML landed 🛬🛬

One thing I love about my job is that at the end of the day my whiteboard might be covered in drawings of decapitated flatworms.

#ICLR 💐 @growai.bsky.social We have 4 posters TODAY ‼️ 🧐 Please come and checkout🤟

#ICLR #BiAlign ‼️🤔Intention understanding and perspective-taking are core theory-of-mind abilities that humans typically develop starting around age 3. However, in VLMs, these two abilities dissociate.🧐 📅 Tomorrow ‼️ April 28, Garnet 216-214 openreview.net/forum?id=rmH... 💐 @growai.bsky.social

#ICLR 🔍 Small poster, big insights ⁉️ 😮 😲 Vision Language Models Know Law of Conservation without Understanding More-or-Less 🙀🙀 Come to our poster at #BiAlign 📷 Room Garnet 216-214 📷 ❗️April 28❗️ openreview.net/forum?id=0fT... 👏 @growai.bsky.social

#ICLR ‼️ We evaluated 209 models and all of them are stochastic parrots 🦜 🙀Models either believe "the bigger the ball, the quicker it falls" (illusions), or, "not matter how big, fall at the same time" (shortcuts). 😲 🗓️ April 28📍 Garnet 214-215 openreview.net/forum?id=B2Q... 👏 @growai.bsky.social

🔨🔧⚙️ Have Vision Language Models solved mechanical reasoning? If you are at @iclr-conf.bsky.social, please come and check out our poster "Probing Mechanical Reasoning in Large Vision Language Models" #ICLR2025 ! 📷Room Garnet 216-214 🗓️April 28 My work at @growai.bsky.social

Our paper from AI at Meta and @bcbl.bsky.social is out on arxiv 🔥 “From Thought to Action: How a Hierarchy of Neural Dynamics Supports Language Production” arxiv.org/abs/2502.07429 How does the brain transform a thought into a sequence of motor actions? Results summarized in 🧵1/8

Are there fundamental barriers to AI alignment once we develop generally-capable AI agents? We mathematically prove the answer is *yes*, and outline key properties for a "safe yet capable" agent. 🧵👇 Paper: arxiv.org/abs/2502.05934

Is there an innate sense of number in the brain? doi.org/10.1093/cerc... #neuroscience

Do children understand all types of visual media in the same way? "Cross-contextual diversity in children’s early understanding of visual media" - a new review paper led by Rebecca Zhu: osf.io/preprints/ps...

Chris Fields and I on the origin of life: www.tandfonline.com/doi/epdf/10.... 🧪

current favorite typo in manuscript: "if the prior is specified with a proper rage..."

One of my favorite science burns: In the late 1770s, Antoine Lavoisier described Joseph Priestley's research on air as "a tissue of experiments almost uninterrupted by reasoning."

Great long read on @e11bio.bsky.social by one of my favorite publications @asimovpress.bsky.social . It’s worth repeating: estimated cost for a whole mouse brain connectome has gone down by a factor 100 over the last couple of years. open.substack.com/pub/cell/p/b...

Shout out to this review by @hugospiers.bsky.social and others www.nature.com/articles/s41... Some sort of hybrid between local Euclidean maps and non-Eucl topo rep (hierarchy? not?) seems like a good start

Nice write up of our recent PNAS article by Bloomberg News: www.bloomberg.com/news/article...

inside you there are two philosophers

New preprint with bhartl.bsky.social, Yanbo Zhang, @drhazan.bsky.social: Heuristically Adaptive Diffusion-Model Evolutionary Strategy arxiv.org/abs/2411.13420

Any sufficiently simple technology is indistinguishable from magic if you're too lazy to understand it. [as I stare at an espresso machine in my lab]