Log inSign up
Hokin Deng
2,854 posts
Image
user avatar
Hokin Deng
@DengHokin
video-reason.com / prev. scientist @Harvard @JohnsHopkins @CarnegieMellon
San Francisco, CA
hokindeng.github.io
Born July 17, 2003
Joined February 2022
243
Following
948
Followers
  • user avatar
    Hokin Deng
    @DengHokin
    Jun 29, 2025
    #ICML #cognition #GrowAI We spent 2 years carefully curated every single experiment (i.e. object permanence, A-not-B task, visual cliff task) in this dataset (total: 1503 classic experiments spanning 12 core cognitive concepts). We spent another year to get 230 MLLMs evaluated
    Image
    112K
  • user avatar
    Hokin Deng
    @DengHokin
    Jun 29, 2025
    Replying to @DengHokin
    🚀 Dive in 👇 🌐 Project: williamium3000.github.io/core-knowledge/ 📄 Paper: arxiv.org/abs/2410.10855 📝 OpenReview: openreview.net/forum?id=EIK6x… 📊 Dataset: huggingface.co/datasets/willi… 💻 Code: github.com/williamium3000… 😎 Team: growing-ai-like-a-child.github.io 💥 Huge thanks to my amazing collaborators
    2.4K
  • user avatar
    Hokin Deng
    @DengHokin
    Jun 29, 2025
    Replying to @DengHokin
    First, MLLMs exhibit a reversed developmental trajectory 📉 compared to humans 📈: they perform better on "higher-level" abilities, sometimes comparable to or even surpassing humans, yet struggle with "lower-level" abilities 🙀, which humans typically develop these "lower-level"
    Image
    5.4K
  • user avatar
    Hokin Deng
    @DengHokin
    Aug 5, 2025
    #embodied All forms of biological intelligence are grounded movements🏃‍♂️ muscles & motor neurons 🧠 emerge before visual cortex & rods & cones in eyes 👁️ Building monocular better-than-mocap-studio #video2motion is our critical step towards human embodied intelligence.
    user avatar
    myolab.ai
    @MyolabAI
    Aug 5, 2025
    💥We are excited to share that our #Video2Animation feature is now live at @MyolabAI's discord servers. We're giving away massive 𝐟𝐫𝐞𝐞 credits for early users. Head now to 👉 discord.gg/Gc9hapPgQg
    Image
    00:00
    4.4K
  • user avatar
    Hokin Deng
    @DengHokin
    Jun 29, 2025
    Replying to @DengHokin
    7) The result is astonishing 😱 All models - either they become totally illusory or they become completely short-cutted. None of the models is even close to core knowledge. No models are able to get both the manipulation tasks and the control tasks right at the same time,
    Image
    2.3K
  • user avatar
    Hokin Deng
    @DengHokin
    Jun 29, 2025
    Replying to @DengHokin
    Started with this old man, Jean Piaget, developmental psychology has become a formal discipline with generations of dedicated scientists and over a century of sustained, yet fruitful, curious endeavors. We first built our CoreCognition framework leveraging Piaget's four-stage
    Image
    Image
    Image
    3.7K
  • user avatar
    Hokin Deng
    @DengHokin
    Jun 29, 2025
    Replying to @DengHokin
    2) The topology of internal cognitive representation of MLLMs is akin to human, suggesting "cognition" as a natural kind. Having 1503 individual cognitive experiments spanning 12 core cognitive concepts on 230 models allows us to interrogate the topology of internal cognitive
    Image
    2.4K
  • user avatar
    Hokin Deng
    @DengHokin
    May 4, 2025
    Finally finish making our website @GrowAiLikeChild growing-ai-like-a-child.github.io 🙌 with @Williamiumli @carrot0817_ @ziqiao_ma @zory_zhang @Pinyuan3 @Pooyanrg and many others 🚶🚶‍♂️🚶‍♀️
    growing-ai-like-a-child.github.io
    GrowAI
    Growing AI like a Child, at Scale, Safely Humans never "learn" intelligence. Humans develop intelligence. Biological lives on this planet take heavy advantage of intelligent primitives embedded in...
    51K
  • user avatar
    Hokin Deng
    @DengHokin
    Jun 29, 2025
    Replying to @DengHokin
    Living in the AI world, all classic cognitive experiments from developmental psychology literature are instantiated as cognitive prototypes. Our cognitive scientists purchase real-world equipments and manually set up physical lab-setting environments to acquire media materials
    Image
    Image
    Image
    3.1K
  • user avatar
    Hokin Deng
    @DengHokin
    May 1, 2024
    Replying to @MudrikNoga
    This is totally unacceptable! I am very sorry to what happened to you.
    2.4K
  • user avatar
    Hokin Deng
    @DengHokin
    Jun 29, 2025
    Replying to @DengHokin
    4) 🧐 🧐 Would Core Knowledge Emerge from Pure Scaling? ‼️‼️‼️Nope‼️‼️‼️ By applying linear regression to the performance data of 230 models with different model sizes & training data sizes, we quantify the scaling effect as the slope of the resulting regression line. The
    Image
    2.1K
  • user avatar
    Hokin Deng
    @DengHokin
    May 14, 2025
    big neuroscience paper dropped in Nature today: memory re-consolidation in hippocampus is supported by neurogenesis
    Content cover image
    Systems consolidation reorganizes hippocampal engram circuitry
    From nature.com
    798
  • user avatar
    Hokin Deng
    @DengHokin
    Jun 29, 2025
    Replying to @DengHokin
    ‼️Results‼️We ran 1503 cognitive experiments spanning 12 core concepts on 230 MLLMs with 11 different prompts for 5 times to get over 3800K inference data points. Here is what we found ... (4/n)
    2.6K
  • user avatar
    Hokin Deng
    @DengHokin
    Jun 29, 2025
    Replying to @DengHokin
    6) Last, we introduce "Concept Hacking" to reveal core knowledge deficiencies in the control experiment set-up. Concept Hacking systematically manipulates the task-relevant features while preserving all task-irrelevant conditions ... (10/n)
    Image
    2K

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms of Service|Privacy Policy|Cookie Policy|Accessibility|Ads info|© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
Advertisement
Advertisement