DYNA-2 is the first robot foundation model pre-trained on over 1 millions hours of egocentric human video – roughly 170 years of continuous waking experience – and establishes a new scaling axis for physical AI by training on pure video instead of scarce action data.

Groundbreaking cross-embodiment transfer across stationary robot arms, humanoid prototypes, and dexterous robotic hands eliminates training bottlenecks and paves a clear path toward 10 million hours of training data – enabling robots to master new physical tasks with just hours of local fine-tuning and delivering zero-shot production-level performance.

REDWOOD CITY, Calif., Aug. 10, 2026 /PRNewswire/ — Dyna Robotics today announced DYNA-2, its flagship World-Action Model (WAM) and the first robot foundation model trained on over 1 million hours of data – equivalent to 170 years of continuous waking experience.

Powered entirely by human egocentric video, DYNA-2 is based on foundational research that demonstrates the first human-to-robot scaling law for robotics, proving that robot performance improves smoothly and predictably with every added hour of human data, without hitting plateaus. This is a paradigm shift for robotic foundation models; by training on video data alone rather than scarce action data or manual teleoperation, Dyna Robotics has discovered a new scaling axis for physical AI, showing that robotics can bypass its greatest bottleneck – scarce, hand-collected teleoperation data – by using video datasets to predictably scale capabilities.

Dyna Robotics’ robots, powered by its previous DYNA-1 model, are already deployed in production in high-demand environments like hotels, restaurants, and laundromats. DYNA-2 is a major step forward in making production-grade, autonomous robots commercially-viable. In high-precision manufacturing tasks, DYNA-2 increased task success rates from 20% to 80–90% purely through pre-training scale, without requiring any changes to post-training data. DYNA-2 enables zero-shot performance at production-level speeds and quality across new deployment sites.

Action data has long choked generalist robotics; collecting physical teleoperation data manually is expensive, slow, and unscalable. DYNA-2 bypasses this bottleneck by establishing a cross-embodiment transfer scaling law. Pre-trained on 1 million hours of human video using a dual next-frame and next-action world-modeling architecture, DYNA-2 enables physical intuition and spatial reasoning gained from human motion to transfer directly to robot hardware, even without seeing a single frame of robot data in pre-training. This dramatically lowers the barrier to training robots on new tasks.

“For years, generalist robotics has been choked by a data bottleneck: collecting physical teleoperation data manually simply cannot scale to general intelligence,” said Dyna Robotics co-founder Jason Ma. “Action data is scarce, but video is everywhere, and with DYNA-2, we showed that physical intuition doesn’t require millions of hours of training on a robot arm – it can be learned directly from human video. By building a World-Action Model that imagines how the physical world moves before taking action, we give robots spatial reasoning and contact physics that traditional vision-language models simply lack and show that physical AI can scale smoothly and predictably, unlocking commercial-grade automation far faster than previously thought possible.”

Production-grade performance in hours

DYNA-2 can be quickly adapted to perform tasks on many different robot platforms with just a few hours of local fine-tuning:

• Aggregated over 15 benchmark tasks, DYNA-2 policies pre-trained with more human data consistently performed better
• In one case, with just 13 minutes of data, DYNA-2 could command a pair of five-fingered robot hands to twist open a bottle cap

Significant performance increases versus Vision-Language-Action models

DYNA-2 shifts the foundation model architecture from Vision-Language-Action (VLA) adaptations to a native WAM built on video generation. In head-to-head physical evaluations against DYNA-1, Dyna Robotics’ VLA model, under matched training steps and datasets, DYNA-2 demonstrated decisive control and task resilience advantages:

• DYNA-2 successfully completed tasks 1.55 times more than DYNA-1 in real-world evaluations. At a customer deployment, DYNA-2 achieved 87% pass rate while DYNA-1 achieved only 46% pass rate.
• DYNA-2 is able to recover from physical disturbances without human intervention when completing tasks requiring dexterous manipulation like chopping food and clearing workspaces, compared to the VLA baseline which failed in a single loop and required manual intervention to recover.
• DYNA-2’s video co-training algorithm improved scores by 133% on instruction-following tasks where robots must perform distinct motions based on user-provided commands

About Dyna Robotics
Dyna Robotics makes general-purpose robots powered by a proprietary embodied AI foundation model that generalizes and self-improves across varied environments with commercial-grade performance. Dyna’s robots have been deployed at customers across multiple industries. Dyna Robotics was founded by repeat founders Lindon Gao and York Yang, who sold Caper AI for $350 million, and former DeepMind research scientist Jason Ma. The company is backed by top investors, including CRV and First Round. Learn more at dyna.co. 

View original content to download multimedia:https://www.prnewswire.com/news-releases/dyna-robotics-unveils-dyna-2-world-action-model-demonstrating-first-true-scaling-law-in-robotics-powered-entirely-by-human-data-302847114.html

SOURCE DYNA Robotics