Today, we’re thrilled to turn the page on embodied-AI manipulation with a major technical breakthrough that finally delivers PERFORMANCE in real-world conditions. Meet Dynamism v1 (DYNA-1). Some may ask: I’ve seen better robot videos, what’s the big deal? The difference is

Incredible stuff. The task isnt so flashy -- but making these methods work really reliably, and running them for 24 hours, is a serious challenge and not something that to my knowledge has been shown before.

I actually don't know if I've seen better robots videos tbh, at least for proving e2e is the way to go. One of the reasons I like this is that it's strong evidence we can actually reach economically-useful performance numbers with e2e vision policies. Have to see the results

Great work for reaching 2.2 9s. Tracking mastery (near 100% in real scenarios) is a signal for being "serious" (thanks Sudeep Dasari) in embodied AI application. Companies should start report 9s or -log10(1-success), ie 1 nine is 90%, 1.3 is 95%...

Sharing some exciting DYNA-1 result: zero-shot environment generalization We put DYNA-1 under test in a completely different environment from our training distribution – with an entirely different background (Dyna Robotics banner) and metal table. The table has a reflective and

We have started taking DYNA-1, our dexterous robust VLA model, to conferences and showcasing it for hours on end! The model run for 3 days, 8 hours each day at #HITEC2025 3 weeks ago with 99.9% overall success rate (dropped 1 towel in day 2). No intervention, it just works :)

I’m thrilled to share that Dyna Robotics has closed a $120M Series A—just as we turned one year old. We’re fortunate to have the backing of incredible partners. This moment in robotics feels historic: the convergence of AI breakthroughs, hardware progress, and urgent labor

Zero shot performance, live

😠💢😵‍💫Tired of endless data collection & fine-tuning every time you try out VLA? Meet RDT2, the first foundation model that zero-shot deploys on any robot arms with unseen scenes, objects & instructions. No collection. No tuning. Just plug and play🚀 Witness a clear sign of

Thanks Ken!

Everyone keeps talking about this demo, if anyone won corl it was these guys

This is a good primer for new robotics investors.

Nice

End-to-end architecture without external memory modules or counting logic. Unlocking more intelligence to production-ready embodied AI.

Excited to share our latest progress on DYNA-1 pre-training! 🤖 The base model now can perform diverse, dexterous tasks (laundry folding, package sorting, …) without any post-training, even in unseen environments. This powerful base also allows extremely efficient fine-tuning

We have been stress testing our model flywheel and seeing strong results in many challenging tasks! Task 1: chopping veggie🧑‍🍳 A test of coordinated tool use that involves asymmetric task and dynamic feedback to make consistent cuts. We used just 70 trajectories to get the

Good robot videos ought to be boring because they're showing it can actually do the thing, over and over and over again.

It's great seeing more results pushing reliable and robust VLA forward since we released our DYNA-1 results 6 months ago! Always exciting to watch the field evolve, and there’s a lot more coming 🚀

Brian is one of the best venture capitalists I’ve had the pleasure of working with. Congrats on the move Brian Zhan !

Impressive work!