Loading video...

Video Failed to Load

Go Home

Echo-2 is a physically-grounded world model from which we can distill meshes, point clouds, or 3DGS scene representations. Directly usable in a myriad of downstream applications from gaming to training robots. Want to build your own world? Try it here:

SpAItial_AI's profile picture

SpAItial AI

4,392 subscribers

21,486 views • 3 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Welcome to 0XROOT🎮 0xROOT is a creative gaming community that brings together passionate players and creators from around the world. We offer an open and inclusive platform where you can share gaming experiences, exchange technical insights, and even participate in collaborative projects. Whether you're a player or a creator, you'll find your joy and opportunities here. Join us and let's build an exciting gaming world together!🫡
0:12

Welcome to 0XROOT🎮 0xROOT is a creative gaming community that brings together passionate players and creators from around the world. We offer an open and inclusive platform where you can share gaming experiences, exchange technical insights, and even participate in collaborative projects. Whether you're a player or a creator, you'll find your joy and opportunities here. Join us and let's build an exciting gaming world together!🫡

0xROOT

19,672 views • 2 years ago

The concept of creating an exact digital replica of the physical world has always fascinated me: environments that look and behave exactly like our everyday reality, precisely captured in the digital domain. This is the essence of 𝐖𝐨𝐫𝐥𝐝 𝐌𝐨𝐝𝐞𝐥𝐬, simulated realities indistinguishable from our own. Generating these models is the core mission behind what we are building at SpAItial AI. True World Models must capture both photorealistic appearance and underlying physics, spatially-consistent across the environment. For static scenes, current models already deliver impressive results, unlocking downstream applications from gaming to 3D design. However, the true frontier lies in modeling dynamics, which will enable the training of AI agents whose learned behaviors can bridge the sim-to-real gap, thus unlocking countless real-world applications.
0:18

The concept of creating an exact digital replica of the physical world has always fascinated me: environments that look and behave exactly like our everyday reality, precisely captured in the digital domain. This is the essence of 𝐖𝐨𝐫𝐥𝐝 𝐌𝐨𝐝𝐞𝐥𝐬, simulated realities indistinguishable from our own. Generating these models is the core mission behind what we are building at SpAItial AI. True World Models must capture both photorealistic appearance and underlying physics, spatially-consistent across the environment. For static scenes, current models already deliver impressive results, unlocking downstream applications from gaming to 3D design. However, the true frontier lies in modeling dynamics, which will enable the training of AI agents whose learned behaviors can bridge the sim-to-real gap, thus unlocking countless real-world applications.

Matthias Niessner

21,673 views • 5 months ago

This also shows up in the representations learned by the model. We plot the model’s representations of human and robot images. As pre-training is scaled up, the representation of humans and robots become more aligned: to a scaled-up model, human videos "look" like robot demos.
0:10

This also shows up in the representations learned by the model. We plot the model’s representations of human and robot images. As pre-training is scaled up, the representation of humans and robots become more aligned: to a scaled-up model, human videos "look" like robot demos.

Physical Intelligence

120,595 views • 7 months ago

Diffusion for virtual worlds: we've trained a new model to create 3D objects from text. And it's 50x faster than any alternative. We made each of these cute characters in just one minute with Genmo's new text-to-3D model. Build your own world at
0:16

Diffusion for virtual worlds: we've trained a new model to create 3D objects from text. And it's 50x faster than any alternative. We made each of these cute characters in just one minute with Genmo's new text-to-3D model. Build your own world at

Genmo

18,532 views • 3 years ago

Whatever you’re building, a game, an animation, or a world of your own, 404 helps you turn ideas into usable 3D assets. Build beautiful organic worlds using 404-generated assets. Every asset in this reel was generated with 404. All you bring is the prompt. Try it out at:
0:15

Whatever you’re building, a game, an animation, or a world of your own, 404 helps you turn ideas into usable 3D assets. Build beautiful organic worlds using 404-generated assets. Every asset in this reel was generated with 404. All you bring is the prompt. Try it out at:

404

15,327 views • 1 month ago

🚨 REP. BRANDON GILL (R-TX) JUST SAID IT PERFECTLY: "The choice to vote for a Democrat Party committed to opening our borders to the world is a choice to commit civilizational suicide." "Everything that directly impacts your life— affordability, safety, cultural stability— all of it is downstream from immigration." 💯💯
0:10

🚨 REP. BRANDON GILL (R-TX) JUST SAID IT PERFECTLY: "The choice to vote for a Democrat Party committed to opening our borders to the world is a choice to commit civilizational suicide." "Everything that directly impacts your life— affordability, safety, cultural stability— all of it is downstream from immigration." 💯💯

Eric Daugherty

29,433 views • 8 days ago

Having a few hours this afternoon after #CVPR2026? Consider visiting Red Rocks 20 minutes outside of Denver! For some inspiration, here's a world processed by SpAItial AI Echo-2 HQ model from a single phone image! Link to the world in🧵
0:19

Having a few hours this afternoon after #CVPR2026? Consider visiting Red Rocks 20 minutes outside of Denver! For some inspiration, here's a world processed by SpAItial AI Echo-2 HQ model from a single phone image! Link to the world in🧵

Ricardo Martin-Brualla

11,381 views • 2 months ago

I only knew Tina 6 months from start to finish but the book is a story of true love and how one dog or person can try to change the world. You can pre-order here
0:15

Sensitive content

I only knew Tina 6 months from start to finish but the book is a story of true love and how one dog or person can try to change the world. You can pre-order here

Niall Harbison

61,642 views • 1 year ago

Evaluating policies on a real robot can be painful. Can we use a world model to get a rough estimate of how good a policy is? Checkout "Evaluating Robot Policies in a World Model". Paper: Demo: Code:
0:10

Evaluating policies on a real robot can be painful. Can we use a world model to get a rough estimate of how good a policy is? Checkout "Evaluating Robot Policies in a World Model". Paper: Demo: Code:

Sherry Yang

36,692 views • 1 year ago

There is hope that this moment can open a path towards a free Iran. That is what the Iranian people deserve : freedom, dignity, and the right to decide their own future. But allow me to make one important point. Seeing the world as it is in no way diminishes our determination to fight for the world we want.
0:18

There is hope that this moment can open a path towards a free Iran. That is what the Iranian people deserve : freedom, dignity, and the right to decide their own future. But allow me to make one important point. Seeing the world as it is in no way diminishes our determination to fight for the world we want.

Ursula von der Leyen

359,766 views • 5 months ago

🚀🌍🚀 Echo-2 is live! It generates high-quality physically grounded 3D scenes instead of just pixels. Check out the open demo to create and explore worlds in real-time! I gave it a picture from my Himalayas trek—it handles the massive scale range really well! 🏔️🌍
0:12

🚀🌍🚀 Echo-2 is live! It generates high-quality physically grounded 3D scenes instead of just pixels. Check out the open demo to create and explore worlds in real-time! I gave it a picture from my Himalayas trek—it handles the massive scale range really well! 🏔️🌍

David Novotny

11,435 views • 3 months ago

Population dynamics can provide insights into domains ranging from health to environmental science. Here we introduce a geospatial foundation model (plus embeddings and code recipes) that could be employed for a variety of downstream tasks. →
0:17

Population dynamics can provide insights into domains ranging from health to environmental science. Here we introduce a geospatial foundation model (plus embeddings and code recipes) that could be employed for a variety of downstream tasks. →

Google AI

41,911 views • 1 year ago

We just pushed a new version of esoterica to github. This is the culmination of around 2 years of work. Massive improvements across the board most notably a modern DX12 renderer. If you want to build your own engine, it's a great starting point!
0:18

We just pushed a new version of esoterica to github. This is the culmination of around 2 years of work. Massive improvements across the board most notably a modern DX12 renderer. If you want to build your own engine, it's a great starting point!

Bobby Anguelov

41,121 views • 24 days ago

POV: You've just entered a realm full of Polygon games, ready to rock your world 🤯🤯 Buy or list gaming NFTs, create your own #web3 tournaments, find everything in the #web3gaming realm here on Aura 😎
0:15

POV: You've just entered a realm full of Polygon games, ready to rock your world 🤯🤯 Buy or list gaming NFTs, create your own #web3 tournaments, find everything in the #web3gaming realm here on Aura 😎

GAMP

8,030,838 views • 3 years ago

how small can you make a world model? we built mira mini, the first reproduction of mira: •⁠ ⁠reproduced in a week from scratch •⁠ ⁠four players, one shared rocket league match, in the browser •⁠ ⁠distilled to 364m params, weights, code, full report: all open. play it here ↓
0:19

how small can you make a world model? we built mira mini, the first reproduction of mira: •⁠ ⁠reproduced in a week from scratch •⁠ ⁠four players, one shared rocket league match, in the browser •⁠ ⁠distilled to 364m params, weights, code, full report: all open. play it here ↓

hugo

60,553 views • 28 days ago

#RugbyScoop | At some point, there has to be accountability from World Rugby. The inconsistency when it comes to Law application & interpretation is really below par. CLIP A - Try Disallowed CLIP B - Try Allowed
0:10

#RugbyScoop | At some point, there has to be accountability from World Rugby. The inconsistency when it comes to Law application & interpretation is really below par. CLIP A - Try Disallowed CLIP B - Try Allowed

Scoop 🐻 ☕️

33,165 views • 1 year ago

When we began testing #GeminiOmni I wanted to see the accuracy of the edits. So I made a tool directly in Google Flow. DIFF TOOL allows you to compare images/videos in realtime or export videos in sync. Try it out or remix it to make it your own.
0:12

When we began testing #GeminiOmni I wanted to see the accuracy of the edits. So I made a tool directly in Google Flow. DIFF TOOL allows you to compare images/videos in realtime or export videos in sync. Try it out or remix it to make it your own.

Nick Matarese

47,540 views • 2 months ago

It was all so we could build homes with robots. All of our work in floorplan AI,and generative CAD modeling, we did all of that, just so that we could build homes with robots. Early on we talked to a robotics engineer from Katerra. It took them $750k to switch from one house to another house. It takes us 25 minutes, and that's if we had a big lunch. P.S. The soundtrack is hardcore punk, lyrics written by me, but everything else is udio.
0:12

It was all so we could build homes with robots. All of our work in floorplan AI,and generative CAD modeling, we did all of that, just so that we could build homes with robots. Early on we talked to a robotics engineer from Katerra. It took them $750k to switch from one house to another house. It takes us 25 minutes, and that's if we had a big lunch. P.S. The soundtrack is hardcore punk, lyrics written by me, but everything else is udio.

Barrett Ames

390,137 views • 1 year ago

Meet #DBRX: a general-purpose LLM that sets a new standard for efficient open source models. Use the DBRX model in your RAG apps or use the DBRX design to build your own custom LLMs and improve the quality of your GenAI applications.
0:20

Meet #DBRX: a general-purpose LLM that sets a new standard for efficient open source models. Use the DBRX model in your RAG apps or use the DBRX design to build your own custom LLMs and improve the quality of your GenAI applications.

Databricks

327,800 views • 2 years ago