Introducing GEN-0, our latest 10B+ foundation model for robots
@GeneralistAI27 тыс. подписчиков
501 601 просмотр
41 комментарий
Комментарии из оригинального поста в X (Twitter)

@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»

@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»

@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»

@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»

@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»

@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»

@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»

@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»

@GeneralistAI
Read more in our blog post, including early notes from large-scale ablations on our pretraining data. Blog:
75 отметок «Нравится»

@xiao_ted
Amazing results and very promising scaling laws!
10 отметок «Нравится»

@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»

@avizurlo
Amazing work! Where'd you source 270k hours of dexterous data?
5 отметок «Нравится»

@grantg07
Are y’all planning on incorporating hands for more complex assembly or just focusing on grippers?
4 отметки «Нравится»

@helper2424
wow, 270k hours is a lot, what is ratio sim/real?
4 отметки «Нравится»

@MarioChan2002
Extremely large data scale.
2 отметки «Нравится»

@JingjingGong_
Impressive work, I am curious about how Harmonic Reasoning works? Anybody any clue?
2 отметки «Нравится»

@SVenkatachalam
Amazing advances for robotics- congrats to the team!
2 отметки «Нравится»

@carlosdponx
jesus guys
2 отметки «Нравится»

@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»

@_advaitpatel
awesome results!
1 отметка «Нравится»




















