Пропустить навигацию
Introducing GEN-0, our latest 10B+ foundation model for robots
0:00 / 0:48

Introducing GEN-0, our latest 10B+ foundation model for robots

Generalist

@GeneralistAI27 тыс. подписчиков

Открыть в X
1 491 отметка «Нравится»СкачатьОригинальный пост

501 601 просмотр

Introducing GEN-0, our latest 10B+ foundation model for robots ⏱️ built on Harmonic Reasoning, new architecture that can think & act seamlessly 📈 strong scaling laws: more pretraining & model size = better 🌍 unprecedented corpus of 270,000+ hrs of dexterous data Read more 👇

41 комментарий

Комментарии из оригинального поста в X (Twitter)

  • Фото профиля Generalist

    @GeneralistAI

    Surpassing the intelligence threshold 🧠 in the high-data regime for robotics, we observe a phase transition ⚡️ at 7B params where smaller models exhibit ossification under data overload, while larger ones continue to improve and can quickly adapt to new tasks.

    162 отметки «Нравится»

  • Фото профиля Generalist

    @GeneralistAI

    Robotics at Generalist is no longer limited by data. GEN-0 is pretrained on our growing dataset of over 270,000 hrs of real, diverse manipulation data (10,000 hrs/week & accelerating). 1,000s of data collection devices/robots in homes, warehouses, and workplaces worldwide🏠🏭💼

    86 отметок «Нравится»

  • Фото профиля Generalist

    @GeneralistAI

    We’ve developed a new approach to training models, Harmonic Reasoning, which creates a "harmonic" interplay between asynchronous, continuous-time streams of sensing and acting tokens. ⚙️🎵 Watch GEN-0 pack a camera. 🤖📸

    162 отметки «Нравится»

  • Фото профиля Generalist

    @GeneralistAI

    GEN-0 models exhibit strong scaling laws, in which more pretraining data and compute consistently (and predictably) improve downstream post-training performance of the model across many tasks. 🔬📈🧠

    104 отметки «Нравится»

  • Фото профиля Generalist

    @GeneralistAI

    📱Packing the phone into the box: here GEN-0 is tasked with gently packing a phone (including its accessory box) into a snug-fit retail box. Slotting in the phone, inserting the accessory box, flipping, and closing the lid, with all tight fits.

    74 отметки «Нравится»

  • Фото профиля Generalist

    @GeneralistAI

    📦🧠🤖🔄 Packing unseen objects - this evaluates GEN-0's generalization and “physical commonsense": reasoning over the highly varied geometry and physics of new objects, nudging and reorienting, packing in differently depending on shape, pushing objects around to make space.

    49 отметок «Нравится»

  • Фото профиля Generalist

    @GeneralistAI

    Cross-Embodiment – GEN-0 architecture works on different robots by design. We have tested our models on various 6DoF, 7DoF, and 16+DoF semi-humanoid robots.

    60 отметок «Нравится»

  • Фото профиля Generalist

    @GeneralistAI

    To scale GEN-0 capabilities, we are constructing the largest and most diverse real-world manipulation dataset ever built 🌍 including every manipulation task humans can think of – from peeling potatoes, to threading bolts – spanning homes, bakeries, warehouses, factories, & more

    113 отметок «Нравится»

  • Фото профиля Generalist

    @GeneralistAI

    Read more in our blog post, including early notes from large-scale ablations on our pretraining data. Blog:

    75 отметок «Нравится»

  • Фото профиля Ted Xiao

    @xiao_ted

    Amazing results and very promising scaling laws!

    10 отметок «Нравится»

  • Фото профиля Dan James

    @ATTlKA

    These demos are, as always from Generalist, incredible. Would love to see more detail on Harmonic Reasoning since that seems like your alternative to PI's real time action chunking. That seems significant enough of an achievement that it warrants a writeup of its own!

    6 отметок «Нравится»

  • Фото профиля avi

    @avizurlo

    Amazing work! Where'd you source 270k hours of dexterous data?

    5 отметок «Нравится»

  • Фото профиля Grant

    @grantg07

    Are y’all planning on incorporating hands for more complex assembly or just focusing on grippers?

    4 отметки «Нравится»

  • Фото профиля Eugene Mironov

    @helper2424

    wow, 270k hours is a lot, what is ratio sim/real?

    4 отметки «Нравится»

  • Фото профиля Tianxing Chen

    @MarioChan2002

    Extremely large data scale.

    2 отметки «Нравится»

  • Фото профиля Jingjing Gong(龚经经)

    @JingjingGong_

    Impressive work, I am curious about how Harmonic Reasoning works? Anybody any clue?

    2 отметки «Нравится»

  • Фото профиля Sandhya Venkatachalam

    @SVenkatachalam

    Amazing advances for robotics- congrats to the team!

    2 отметки «Нравится»

  • Фото профиля Carlos DP 🤖🇺🇸

    @carlosdponx

    jesus guys

    2 отметки «Нравится»

  • Фото профиля Jonathan Scholz

    @JonathanScholz2

    There's a *lot* to be impressed by in this post, but the biggest thing for me is their early commitment to a scalable data collection strategy (UMI-style in their case) This is how robotics 2.0 companies should be built

    2 отметки «Нравится»

  • Фото профиля underscore advait patel

    @_advaitpatel

    awesome results!

    1 отметка «Нравится»