Sign in

Hokin

@hokin.bsky.social
46 followers 69 following 90 posts

Philosopher, Scientist, Engineer hokindeng.github.io

PostsRepliesMedia
Hokin @hokin.bsky.social · 18/11/2025
Congratulations to @tomerullman.bsky.social on official release! For everyone, my disagreements on this paper has also already been accepted by NeurIPS SpaVLE this year. link: arxiv.org/abs/2510.20835
arxiv.org
Rethinking the Simulation vs. Rendering Dichotomy: No Free Lunch in Spatial World Modelling
Spatial world models, representations that support flexible reasoning about spatial relations, are central to developing computational models that could operate in the physical world, but their precis...
000
Hokin @hokin.bsky.social · 07/11/2025
developmental embodiedment 😎 #DevelopmentalEmbodiedment #GrowAI
020
Hokin @hokin.bsky.social · 04/11/2025
‼️ 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)
241
Hokin @hokin.bsky.social · 02/11/2025
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)
131
Hokin @hokin.bsky.social · 01/11/2025
Very cool work !
010
Hokin @hokin.bsky.social · 01/11/2025
best Halloween costume this year
010
Reposted by Hokin
Tobias Gerstenberg @tobigerstenberg.bsky.social · 02/08/2025
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.
16414
Reposted by Hokin
David Barner @drbarner.bsky.social · 02/08/2025
Susan Carey mic-drop at #cogsci2025. "There are no innate concepts: Discuss"
2358
Hokin @hokin.bsky.social · 30/06/2025
#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 ✅
1139
Hokin @hokin.bsky.social · 13/06/2025
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 ⬇️
120
Reposted by Hokin
Paul Linton @lintonvision.bsky.social · 12/06/2025
Beautiful to see this initiative from a group of like minded PhD students collaborating together! 🚀
194
Hokin @hokin.bsky.social · 12/06/2025
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 😎
165
Hokin @hokin.bsky.social · 03/06/2025
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
010
Reposted by Hokin
Philip Ball @philipcball.bsky.social · 31/05/2025
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...
nature.com
DNA-guided transcription factor interactions extend human gene regulatory code - Nature
A large-scale analysis of DNA-bound transcription factors (TFs) shows how the presence of DNA markedly affects the landscape of TF interactions, and identifies composite motifs that are recognized by ...
1019868
Hokin @hokin.bsky.social · 29/05/2025
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...
nature.com
The pivot penalty in research - Nature
An analysis of millions of scientific papers and patents reveals a ‘pivot penalty’ when researchers shift direction, with the impact of studies decreasing rapidly the further they move from their prev...
010
Reposted by Hokin
Aran Nayebi @anayebi.bsky.social · 28/05/2025
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.
3236
Hokin @hokin.bsky.social · 27/05/2025
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.
110
Hokin @hokin.bsky.social · 24/05/2025
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
0215
Reposted by Hokin
Paul Frankland @franklandlab.bsky.social · 14/05/2025
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
rdcu.be
Systems consolidation reorganizes hippocampal engram circuitry
Nature - A study shows that loss of memory precision associated with systems consolidation can be explained by neurogenesis-dependent reorganization of engram circuitry within the hippocampus over...
1522197
Reposted by Hokin
bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 12/05/2025
Hippocampal reactivation of planned trajectories is required for effective goal choice in an allocentric memory task www.biorxiv.org/content/10.1101/202…
0254
Reposted by Hokin
Sam Gershman @gershbrain.bsky.social · 10/05/2025
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.
4381
Reposted by Hokin
Stanislas Dehaene @standehaene.bsky.social · 06/05/2025
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....
pnas.org
Perceptual integration without conscious access | PNAS
The visual system has the remarkable ability to integrate fragmentary visual input into a perceptually organized collection of surfaces and objects...
3389
Reposted by Hokin
Patrick Mineault @patrickmineault.bsky.social · 05/05/2025
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...
d2jud02ci9yv69.cloudfront.net
In Search of the Engram in LLMs: A Neuroscience Perspective on the Memory Functions in AI Models | ICLR Blogposts 2025
Large Language Models (LLMs) are enhancing our daily lives but also pose risks like spreading misinformation and violating privacy, highlighting the importance of understanding how they process and st...
0164
Hokin @hokin.bsky.social · 05/05/2025
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🚶‍♂️🚶‍♀️🚶
growing-ai-like-a-child.github.io
GrowAI
Growing AI like a Child, at Scale Humans never "learn" intelligence. Humans develop intelligence. Biological lives on this planet take heavy advantage of intelligent primitives embedded in their genes...
043
Hokin @hokin.bsky.social · 01/05/2025
#ICML landed 🛬🛬
031
Reposted by Hokin
Sam Gershman @gershbrain.bsky.social · 29/04/2025
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.
1271
Hokin @hokin.bsky.social · 28/04/2025
#ICLR 💐 @growai.bsky.social We have 4 posters TODAY ‼️ 🧐 Please come and checkout🤟
021
Hokin @hokin.bsky.social · 27/04/2025
#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
021
Hokin @hokin.bsky.social · 27/04/2025
#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
021
Hokin @hokin.bsky.social · 26/04/2025
#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
061
Hokin @hokin.bsky.social · 26/04/2025
🔨🔧⚙️ 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
051
Reposted by Hokin
Primate Research and News @ourprimatepast.bsky.social · 18/02/2025
news.mongabay.com
Bonobos can recognize ignorance and help, a new ‘milestone’ in ape intelligence
Bonobos, one of humanity’s closest relatives, can tell when a human doesn’t know something and steps in to help — a cognitive ability never before identified in nonhuman apes, a study found. Researche...
0104
Reposted by Hokin
Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 18/02/2025
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
1208
Reposted by Hokin
Aran Nayebi @anayebi.bsky.social · 13/02/2025
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
2124
Reposted by Hokin
Earl K. Miller @earlkmiller.bsky.social · 15/02/2025
Is there an innate sense of number in the brain? doi.org/10.1093/cerc... #neuroscience
doi.org
Is there an innate sense of number in the brain?
Abstract. The approximate number system or «sense of number» is a crucial, presymbolic mechanism enabling animals to estimate quantities, which is essentia
2364
Reposted by Hokin
Mike Frank @mcxfrank.bsky.social · 14/02/2025
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...
Table 1 from paper: recognition and reference evidence for perception of different types of visual media by infants, toddlers, and preschoolers.
1329
Reposted by Hokin
Mike Levin @drmichaellevin.bsky.social · 17/02/2025
Chris Fields and I on the origin of life: www.tandfonline.com/doi/epdf/10.... 🧪
tandfonline.com
Life, its origin, and its distribution: a perspective from the Conway-Kochen Theorem and the Free Energy Principle
43012
Reposted by Hokin
Tomer Ullman @tomerullman.bsky.social · 11/02/2025
current favorite typo in manuscript: "if the prior is specified with a proper rage..."
2324
Reposted by Hokin
Sam Gershman @gershbrain.bsky.social · 11/02/2025
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."
1334
Reposted by Hokin
Patrick Mineault @patrickmineault.bsky.social · 09/02/2025
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...
open.substack.com
Barcoding Brains
Connectomics — a technique that maps physical connections between neural cells — is expensive and inefficient. E11 Bio, a non-profit research group, is designing a tool to expedite progress.
0132
Reposted by Hokin
Jim Thompson @jimthommo.bsky.social · 08/02/2025
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
nature.com
From cognitive maps to spatial schemas - Nature Reviews Neuroscience
Schemas are structured bodies of prior knowledge that reflect common patterns of information from related experiences. In this Review, Farzanfar et al. discuss evidence for spatial schemas, how they f...
072
Reposted by Hokin
Hugo Spiers @hugospiers.bsky.social · 07/02/2025
Nice write up of our recent PNAS article by Bloomberg News: www.bloomberg.com/news/article...
bloomberg.com
How London’s Taxi Drivers Navigate the City Without GPS
Drivers of the city’s black cabs can teach satellite navigation apps a few things about how to plan the most efficient route, a new study says.
0133
Reposted by Hokin
Tomer Ullman @tomerullman.bsky.social · 31/01/2025
inside you there are two philosophers
Thomas Nagel, looking bored, asking "What is it like to be a bat?" Thomas Nagel, looking fascinated, asking "what is it like to bat a bee?"
191
Reposted by Hokin
Mike Levin @drmichaellevin.bsky.social · 06/02/2025
New preprint with bhartl.bsky.social, Yanbo Zhang, @drhazan.bsky.social: Heuristically Adaptive Diffusion-Model Evolutionary Strategy arxiv.org/abs/2411.13420
arxiv.org
Heuristically Adaptive Diffusion-Model Evolutionary Strategy
Diffusion Models represent a significant advancement in generative modeling, employing a dual-phase process that first degrades domain-specific information via Gaussian noise and restores it through a...
0195
Reposted by Hokin
Sam Gershman @gershbrain.bsky.social · 31/01/2025
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]
2411