Skip to content
Trending eventDeveloping

Nature Will launches Natura-1, a 50-billion-parameter foundation model for dexterous robot hands

1 reports1 reporting sourcesUpdated 6 hours ago

Overview

Event synthesis

Nature Will announced Natura-1, a 50-billion-parameter mixture-of-experts model trained on over 1 million hours of egocentric human data. The model operates at a 100-millisecond control loop to enable zero-shot instruction following and sustained manipulation for advanced robotics applications.

Generated from attributed reports · Updated 5 hours ago

Event evidence and corrections

1 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.

Data origin: human egocentric
Supporting report

“Nature Will , a physical AI lab dedicated to building physical AGI, has announced the launch of Natura-1, a 50-billion-parameter physical general foundation model for dexterous hand control and zero-shot instruction following in advanced robotics applications. Pre-trained on over 1 million hours of egocentric human data, the Natura-1 combines instruction following with the ability to manipulate to changing task condi”

Exact source · revision 2

robotics-automation-news

Reported quantity · parameter count: 50 other · Basis not reported
Supporting report

“Nature Will launches 50-billion-parameter AI model for dexterous robot hands”

Exact source · revision 2

robotics-automation-news

Reported quantity · training hours: 1 other · aggregate sensor hours
Supporting report

“Nature Will , a physical AI lab dedicated to building physical AGI, has announced the launch of Natura-1, a 50-billion-parameter physical general foundation model for dexterous hand control and zero-shot instruction following in advanced robotics applications. Pre-trained on over 1 million hours of egocentric human data, the Natura-1 combines instruction following with the ability to manipulate to changing task condi”

Exact source · revision 2

robotics-automation-news

Reported quantity · control loop latency: 100 other · Basis not reported
Supporting report

“er in a foundation model for dexterous hands, applicable to any field where fine or delicate manipulations are required as part of the creation process. Built on a 50 billion parameter mixture-of-experts model trained jointly on language, images, video, and action, Natura-1 operates at a 100-millisecond control loop to unify language, vision, and high-degree-of-freedom action that connects language-directed behavior”

Exact source · revision 2

robotics-automation-news

Reported quantity · model parameter count: 50 other · Basis not reported
Supporting report

“with the physical control. Ning Ding, CEO of Nature Will, says: “We believe general models that can handle every task must exist, and that those models must utilize dexterous hands. “Natura-1 is our first step towards models that scale from human experience, building infrastructure that enables us to create the model from the ground up and that allows it to scale to any application. “The Natura-1 is a 50-billion-para”

Exact source · revision 2

robotics-automation-news

Dataset · modalities: language · Differing source assertions
Supporting report

“er in a foundation model for dexterous hands, applicable to any field where fine or delicate manipulations are required as part of the creation process. Built on a 50 billion parameter mixture-of-experts model trained jointly on language, images, video, and action, Natura-1 operates at a 100-millisecond control loop to unify language, vision, and high-degree-of-freedom action that connects language-directed behavior”

Exact source · revision 2

robotics-automation-news

Dataset · modalities: images · Differing source assertions
Supporting report

“er in a foundation model for dexterous hands, applicable to any field where fine or delicate manipulations are required as part of the creation process. Built on a 50 billion parameter mixture-of-experts model trained jointly on language, images, video, and action, Natura-1 operates at a 100-millisecond control loop to unify language, vision, and high-degree-of-freedom action that connects language-directed behavior”

Exact source · revision 2

robotics-automation-news

Dataset · modalities: video · Differing source assertions
Supporting report

“er in a foundation model for dexterous hands, applicable to any field where fine or delicate manipulations are required as part of the creation process. Built on a 50 billion parameter mixture-of-experts model trained jointly on language, images, video, and action, Natura-1 operates at a 100-millisecond control loop to unify language, vision, and high-degree-of-freedom action that connects language-directed behavior”

Exact source · revision 2

robotics-automation-news

Dataset · modalities: action · Differing source assertions
Supporting report

“er in a foundation model for dexterous hands, applicable to any field where fine or delicate manipulations are required as part of the creation process. Built on a 50 billion parameter mixture-of-experts model trained jointly on language, images, video, and action, Natura-1 operates at a 100-millisecond control loop to unify language, vision, and high-degree-of-freedom action that connects language-directed behavior”

Exact source · revision 2

robotics-automation-news

Dataset · tasks: dexterous hand control · Differing source assertions
Supporting report

“Nature Will , a physical AI lab dedicated to building physical AGI, has announced the launch of Natura-1, a 50-billion-parameter physical general foundation model for dexterous hand control and zero-shot instruction following in advanced robotics applications. Pre-trained on over 1 million hours of egocentric human data, the Natura-1 combines instruction following with the ability to manipulate to changing task condi”

Exact source · revision 2

robotics-automation-news

Dataset · tasks: zero-shot instruction following · Differing source assertions
Supporting report

“Nature Will , a physical AI lab dedicated to building physical AGI, has announced the launch of Natura-1, a 50-billion-parameter physical general foundation model for dexterous hand control and zero-shot instruction following in advanced robotics applications. Pre-trained on over 1 million hours of egocentric human data, the Natura-1 combines instruction following with the ability to manipulate to changing task condi”

Exact source · revision 2

robotics-automation-news

Dataset · tasks: manipulation · Differing source assertions
Supporting report

“Nature Will , a physical AI lab dedicated to building physical AGI, has announced the launch of Natura-1, a 50-billion-parameter physical general foundation model for dexterous hand control and zero-shot instruction following in advanced robotics applications. Pre-trained on over 1 million hours of egocentric human data, the Natura-1 combines instruction following with the ability to manipulate to changing task condi”

Exact source · revision 2

robotics-automation-news

Report timeline

Follow attributed reports and material updates.

11/9
  1. Robotics & Automation News
    Nature Will launches Natura-1, a 50-billion-parameter foundation model for dexterous robot hands

    Nature Will announced Natura-1, a 50-billion-parameter mixture-of-experts model trained on over 1 million hours of egocentric human data. The model operates at a 100-millisecond control loop to enable zero-shot instruction following and sustained manipulation for advanced robotics applications.

Event coverage history

Current attention 9·Peak within the comparable range 10(2026-11-09 21:00 UTC)·Change within the comparable range over 24 hours –

02.557.5102026-11-0921:002026-11-0922:002026-11-1000:002026-11-1001:00

The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.

Timezone · UTC

Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).