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

Who needs feet, anyway?

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

Robots just got their Ivy League upgrade. GEN-0 sounds like the kid who aced both calculus and karate. With 270,000 hours of data, it probably folds laundry with perfect choreography. At this rate, the term “hands-on learning” will soon apply more to machines than humans.

Huge leap forward for robotics 🤖

only up from here

amazing

impressive, can't wait for demos!

👀

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

Whoa, GEN-0 sounds like the robot version of Tony Stark! 🤖✨ Can't wait to see it in action!

The 7B phase transition is critical - it's showing us the minimum viable intelligence threshold for embodied learning. Below 7B: models exhibit ossification under diverse sensorimotor data. The weights can't absorb new patterns without catastrophic forgetting. Above 7B: continued scaling improvements. This is the first time we're seeing LLM-style scaling laws validated for robotics foundation models with this level of rigor. But Harmonic Reasoning is the real innovation here. It solves a fundamental problem: language models can "pause to think" because digital time is discrete. Robots can't - physics doesn't stop. Solution: asynchronous, continuous-time streams of sensing and acting tokens. The model doesn't do "perceive → reason → act" sequentially. It harmonizes all three in parallel, like how humans process visual input while simultaneously planning and executing motor commands. This is architecturally different from traditional VLA models that still operate in discrete time steps. GEN-0 treats sensorimotor control as a continuous process, enabling: - Sub-100ms reactive reflexes - Predictive control (act on expected state, not just current) - Multi-timescale reasoning (strategic + reactive simultaneously) 270K+ hours of dexterous data + strong scaling laws + continuous control architecture = the first deployment-ready foundation model for generalist robotics. Mann!! If this holds at scale, sequential action models will look as outdated as batch processing in a streaming world.

10B parameters of motion — the moment reasoning meets embodiment, robotics stops being mechanical and starts being cognitive.

impressive work! any plans to open source this, or at least provide an api/sdk to train and evaluate the policy? how can the community independently verify the scaling/ossification and power-law claims beyond the blog demos ; e.g. public checkpoints, eval suites, or third-party benchmarks?

Even collecting this much data in China would cost between $2 million and $3 million. It's important to note that data costs in China are among the lowest in the world.

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!

Congratulations on this exciting milestone!

Impressive on paper, now prove it in a messy kitchen

Amazing results and very promising scaling laws!

Fascinating

270k+ hours of dexterous data is wild. Getting that much high-quality, multimodal training data must’ve been a huge undertaking. Curious how it generalizes across different robot platforms.

will models trained on this data scale to other embodiments? for example if you add more DOFs to the gripper or make it more anthropomorphic?

Ginormous dex data. Quality > quantity. How well do the results translate from sim to real-world non-clinical environment?

holy crap. huge if true is everyone else cooked?

awesome results!

Amazing advances for robotics- congrats to the team!

Made in the USA NDAA Compliant AI NVIDIA Flight Controllers. Ready to scale your autonomous drone production.