We are back again :) After three weeks of quiet building.
Introducing Genesis World 1.0, our latest simulation platform, the second release in our full-stack suite. Open-sourced.
Robotics is still bottlenecked by the 1× speed of the physical world. Every model, checkpoint, and data recipe eventually needs to be tested on physical hardware, slowly, expensively, and with limited coverage.
One hour in reality can become 100 days in simulation. That is how robotics model iteration moves from a wall-clock bottleneck to a compute problem.
To make this work, simulation has to be both fast and trustworthy.
Over the past year, we rebuilt the entire stack: a GPU-accelerated cross-platform compiler, penetration-free multi-physics contact solvers, unified rigid and deformable physics, and a photo-realistic renderer purpose-built for physical AI applications.
We built Nyx, a high-performance path-traced rendering engine for robotics application.
Genesis World 1.0 achieves near realtime performance with our latest development for penetration-free IPC solver, supporting various types of deformables beyond rigid bodies. It supports contact-rich, dexterous manipulation simulation across different embodiments: unitree, sharpa, wuji, genesis hand and various types of grippers.
Under the hood is Quadrants, our effort in pushing forward cross-platform GPU-accelerated computation. Quadrants started as a fork of Taichi, and we rebuilt most of the critical parts for optimizing simulation workloads, giving 10x faster launch time and up to 4.6x runtime performance compared to the initial Genesis release.
Together, they bring us to an unprecedentedly low sim-to-real gap, enabling zero-shot real-to-sim model evaluation and much faster iteration of GENE.
All available today.
Genesis World 1.0: https://t.co/aknCM3eqws
Quadrants: https://t.co/uXqPNI4cb6
Nyx: https://t.co/R8j0djqGnV
11/11
Today, we are more convinced than ever: human-level manipulation is no longer a question of if. It's a question of how fast we get there.
We are approaching the endgame for robotics.
Read more about GEN-26.5 in our technical blog post: https://t.co/tD2USOvpBB
4/
Rubik’s Cube solving has been a long-standing challenging benchmark for robotic manipulation. The task requires fine-grained control under the geometric and kinematic constraints imposed by the cube itself. Prior state-of-the-art is still the single-handed solver from OpenAI’ in 2019. For the first time, we can solve a Rubik's Cube using two hands together, powered by GENE.
So lucky to live in this era, working on the most exciting problem with the best people at the best place: Genesis. It feels amazing that the ambitious plans can be achieved by having conviction, working the full stack from the lowest level up, and carefully getting every seemingly small detail right. Robotics is a long-term and systematic problem. This is a great milestone where every piece comes together, and we're just getting started. More to come!
We are back. After one year of quiet building.
Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability.
For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans.
Solving it means rethinking the whole stack from the ground up:
- A robotics-native foundation model.
- A 1:1 human-like robotic hand.
- A noninvasive data collection glove for motion, force, and touch.
- A simulator that turns weeks of experiments into minutes.
GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm.
Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on)
We are approaching the endgame for robotics.
And this is just a beginning.
We are back. After one year of quiet building.
Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability.
For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans.
Solving it means rethinking the whole stack from the ground up:
- A robotics-native foundation model.
- A 1:1 human-like robotic hand.
- A noninvasive data collection glove for motion, force, and touch.
- A simulator that turns weeks of experiments into minutes.
GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm.
Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on)
We are approaching the endgame for robotics.
And this is just a beginning.
Today, We’re launching Genesis AI — a global physical AI lab and full-stack robotics company — to build generalist robots and unlock unlimited physical labor.
We’re backed by $105M in seed funding from @EclipseVentures, @khoslaventures, @Bpifrance, HSG, and visionaries including @ericschmidt and @Xavier75 .
General-purpose robots will be the next chapter in human history. Half of global GDP is physical. Less than 5% is automated. Today’s robots are too narrow, rigid, and expensive to scale. We need a new generation of adaptable, foundation-model-driven systems.
We are a new generation of robotics builders, united by a shared mission to push the boundaries of physical AI. Our team brings together the minds behind many recent key advances spanning robotics, imitation learning, RL, simulation, GPU compilers, and foundation models — bridging historically siloed communities.
We co-created UMI and Diffusion Policy, pioneered RL for superhuman drone racing, and scaled robotic data pipelines at NVIDIA GR00T. We introduced the paradigm of generative simulation, built Genesis, Jiminy, Flightmare, and GVBD Voxels, and invented the IPC algorithm. We built cross-platform GPU compilers VeriGPU, DeepCL, Coriander, and the original PyTorch, and industry-leading rendering engines at Epic, Unity, and Google. We also spearheaded the first multimodal foundation models at Mistral AI and Apple Intelligence.
Now, we’ve come together at Genesis AI to close the loop, and build what’s next.
Join us → https://t.co/RQdf8UzXhO
We’re excited to share some updates on Genesis since its release:
1. We made a detailed report on benchmarking Genesis's speed and its comparison with other simulators (https://t.co/Wkr7gJtAGh)
2. We’ve launched a Discord channel and a WeChat group to foster communications between users and contributors
3. We released Genesis 0.2.1 today with new features including faster cached kernel loading, docker file support, smoke simulation, RL training example for drones, multilingual documentation support, together with various new APIs. A heartfelt thank you to the open-source community for contributing to this collaborative effort!
Everything you love about generative models — now powered by real physics!
Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics simulation platform designed for general-purpose robotics and physical AI applications.
Genesis's physics engine is developed in pure Python, while being 10-80x faster than existing GPU-accelerated stacks like Isaac Gym and MJX. It delivers a simulation speed ~430,000 faster than in real-time, and takes only 26 seconds to train a robotic locomotion policy transferrable to the real world on a single RTX4090 (see tutorial: https://t.co/bEkIlCKqdf).
The Genesis physics engine and simulation platform is fully open source at https://t.co/DhBv7NdyqH. We'll gradually roll out access to our generative framework in the near future.
Genesis implements a unified simulation framework all from scratch, integrating a wide spectrum of state-of-the-art physics solvers, allowing simulation of the whole physical world in a virtual realm with the highest realism.
We aim to build a universal data engine that leverages an upper-level generative framework to autonomously create physical worlds, together with various modes of data, including environments, camera motions, robotic task proposals, reward functions, robot policies, character motions, fully interactive 3D scenes, open-world articulated assets, and more, aiming towards fully automated data generation for robotics, physical AI and other applications.
Open Source Code: https://t.co/DhBv7NdyqH
Project webpage: https://t.co/SBNyhFB0yn
Documentation: https://t.co/3yuBoaealV
1/n
Can GPTs generate infinite and diverse data for robotics?
Introducing RoboGen, a generative robotic agent that keeps proposing new tasks, creating corresponding environments and acquiring novel skills autonomously!
code: https://t.co/PuU2d3WMEs
👇🧵
(better with audio)