LightOrigins's banner

LightOrigins

@LightOrigins_ • 1,342 subscribers

Light Origins brings foundation-model intelligence into the physical world so machines can perceive, reason, and act.

Shorts

Every robot should see, understand, and explore the physical world. Introducing LightNav-0: one generalist navigation brain by Light Origins. Any robot. Any task. Anywhere. Open source. Out of the box. Coming soon.

Every robot should see, understand, and explore the physical world. Introducing LightNav-0: one generalist navigation brain by Light Origins. Any robot. Any task. Anywhere. Open source. Out of the box. Coming soon.

58,526 просмотров

Robots won’t scale if every failure brings them to a halt. We train a generalist Transformer policy across a wide range of hardware impairments, enabling it to adapt to the robot’s changing capabilities at runtime through whole-body in-context learning. Meet Light REACT.

Robots won’t scale if every failure brings them to a halt. We train a generalist Transformer policy across a wide range of hardware impairments, enabling it to adapt to the robot’s changing capabilities at runtime through whole-body in-context learning. Meet Light REACT.

12,558 просмотров

We train humanoid robots to vault obstacles, climb platforms, and cross terrain they’ve never seen—all from a single perceptive, whole-body policy. It decides whether to walk, climb, or vault, and switches between skills on its own. No skill labels. No state machines. No motion generators at inference. The recipe is real → sim → real, seeded by one video per skill. Here’s how it works ⬇️

We train humanoid robots to vault obstacles, climb platforms, and cross terrain they’ve never seen—all from a single perceptive, whole-body policy. It decides whether to walk, climb, or vault, and switches between skills on its own. No skill labels. No state machines. No motion generators at inference. The recipe is real → sim → real, seeded by one video per skill. Here’s how it works ⬇️

12,379 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Autonomous. By Light Origins. Stay tuned.

Autonomous. By Light Origins. Stay tuned.

48,554 просмотров • 2 месяцев назад

Introducing Light-O1, a whole-body intelligence model scaled through human action pretraining. • Human action at scale: We learn from structured human actions recovered from internet videos, capturing a scale and diversity that robot data collection alone struggles to match. • Cross-embodiment transfer scaling law: Scaling human action pretraining yields power-law reductions in prediction error across embodiments. • Whole-body intelligence: Adapted to different humanoids, Light-O1 coordinates movement, posture, and manipulation to autonomously perform household tasks.

Introducing Light-O1, a whole-body intelligence model scaled through human action pretraining. • Human action at scale: We learn from structured human actions recovered from internet videos, capturing a scale and diversity that robot data collection alone struggles to match. • Cross-embodiment transfer scaling law: Scaling human action pretraining yields power-law reductions in prediction error across embodiments. • Whole-body intelligence: Adapted to different humanoids, Light-O1 coordinates movement, posture, and manipulation to autonomously perform household tasks.

28,182 просмотров • 1 месяц назад

Our humanoid robot vaults, climbs, and crosses terrain it’s never seen before—deciding which move to use in real time, completely on its own 🤖 Real → sim → real. 👇

Our humanoid robot vaults, climbs, and crosses terrain it’s never seen before—deciding which move to use in real time, completely on its own 🤖 Real → sim → real. 👇

32,139 просмотров • 3 месяцев назад

Introducing LightNav-0, our first general-purpose navigation brain. Open-sourced starting today. Trained entirely in simulation, so it scales. See scalable real2sim2real transfer across robots, tasks, and scenes.

Introducing LightNav-0, our first general-purpose navigation brain. Open-sourced starting today. Trained entirely in simulation, so it scales. See scalable real2sim2real transfer across robots, tasks, and scenes.

14,853 просмотров • 2 месяцев назад

Больше нет контента для загрузки