Jason Ma
@JasonMa2020
Co-founder & AI @DynaRobotics Prev: @GoogleDeepMind, @NVIDIAAI, @MetaAI, @Penn, @Harvard.
Introducing Dynamism v1 (DYNA-1) by @DynaRobotics – the first robot foundation model built for round-the-clock, high-throughput dexterous autonomy. Here is a time-lapse video of our model autonomously folding 850+ napkins in a span of 24 hours with • 99.4% success rate — zero…
Jason @JasonMa2020 talks about Foundation Reward Models for Robot Learning at the Programmatic Representations for Agent Learning workshop at #ICML2025!
Our #ICML2025 Programmatic Representations for Agent Learning workshop will take place tomorrow, July 18th, at the West Meeting Room 301-305, exploring how programmatic representations can make agent learning more interpretable, generalizable, efficient, and safe! Come join us!
Looking forward to sharing some of my thoughts on how programmatic outputs from large foundation models can accelerate robot learning!
Our #ICML2025 Programmatic Representations for Agent Learning workshop will take place tomorrow, July 18th, at the West Meeting Room 301-305, exploring how programmatic representations can make agent learning more interpretable, generalizable, efficient, and safe! Come join us!
Introducing Muscle v0 -- infinite degrees of freedom, from @DaxoRobotics. A different mountain to climb - with a far more beautiful peak. We built this from the ground up: - Ultra-dexterous - Built for machine learning - Durable and robust More below (1/n)
happy 4th! it was really fun to play with this human robot interaction🤖🇺🇸
Happy July 4th from Dyna! 🇺🇸🇺🇸
- new demo task - new environment with hardware we just setup - robust to changes in lighting, people visible, etc - production ready quality and robustness - real businesses that are interested bc it provides real value it's a cook or get cooked world and we're cooking
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 :)
Our DYNA-1’s robustness on folding tasks is just incredible! As a roboticist, I didn’t know HITEC, but going to that conference brought us hundreds of customers. Anyone interested in seeing our demo in more robot learning conferences?
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 :)
It's so satisfying to watch our models just do the task on demand; human like and no downtime
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 :)
Presenting DemoDiffusion: An extremely simple approach enabling a pre-trained 'generalist' diffusion policy to follow a human-demonstration for a novel task during inference One-shot human imitation *without* requiring any paired human-robot data or online RL 🙂 1/n
Excited to be speaking at #Actuate2025!
Robots that actually work 24/7, no babysitting, are the holy grail of robotics. @JasonMa2020 and the team at @DynaRobotics realized the standard recipes for training robot foundation models lacked real-world 'performance' — high throughput, high quality, every time. Enter…
Giving a talk tomorrow at the Foundation Models for Interactive Robot Learning workshop (lfmrss2025.weebly.com) at RSS! Will cover some @DynaRobotics results too! What would people like to see?
I am attending #RSS this week! Participating in the Pioneers workshop as well as giving a talk at the Foundation Models for Interactive Robot Learning workshop. Happy to meet up and chat if you are around!
I ll be hanging out at the LeRobot Hackathon this weekend, come say hi!
The impact of accessible low-cost robot arms and the community that’s built up around @LeRobotHF has been so awesome to see! 🤖 🚀 I am honored to be a guest judge this weekend at the Global LeRobot hackathon’s SF location. Thanks to @BitRobotNetwork for hosting.
Nice work on how to go beyond BC by learning to search using world and reward models! The nice thing is that you don't need to collect any additional data.
Say ahoy to 𝚂𝙰𝙸𝙻𝙾𝚁⛵: a new paradigm of *learning to search* from demonstrations, enabling test-time reasoning about how to recover from mistakes w/o any additional human feedback! 𝚂𝙰𝙸𝙻𝙾𝚁 ⛵ out-performs Diffusion Policies trained via behavioral cloning on 5-10x data!
Attending #CVPR2025 in Nashville to present ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos. I'll be giving a spotlight talk and presenting a poster both today and tomorrow. Looking forward to chatting with everyone! Wednesday 📍10:30am-11:00am ExHall D, Poster…
Very cool new (to me) video from Dyna robotics, showing box packing and even making a sandwich.
I'm attending #ICRA2025 this week! Happy to chat about Dyna and all things embodied AI. DMs are open!