World Labs ✓
@theworldlabs · San Francisco, CA · joined 01 Jan 2024
World Labs is a leading spatial intelligence company building frontier models that can perceive, generate, reason, and interact with virtual and physical worlds
109 943Followers
53Following
560Posts total
1.5MViews on collected posts
Latest posts
Looking for new posts…
@theworldlabs let's see some physics, frameboy.
755 views · 7 likes
· 0 reposts · 0 replies
Open on X →
To learn more about Atlas and sign up for early access, check out:
https://t.co/SHjFaNWedP
3K views · 34 likes
· 1 reposts · 0 replies
Open on X →
Atlas is an autoregressive model that generates frames one at a time. We have optimized a version of Atlas that generates in real-time, allowing you to interactively explore worlds that are generated on-the-fly. https://t.co/psKrFBi9Av
8.6K views · 100 likes
· 5 reposts · 5 replies
Open on X →
0:21
Atlas maintains 3D consistency during generation by building up a spatial context of inputs and previously generated frames.
You can explore reconstructions of real-world scenes by adding real-world images to the spatial context. https://t.co/k0dWZbRIKm
9K views · 59 likes
· 4 reposts · 3 replies
Open on X →
0:50
@theworldlabs Very nice results! The resulting artefacts look pretty similar to LoD popping in modern 3D games. Was this model trained with some footage from games which made it learn that LoD popping would be a good thing?
195 views · 1 likes
· 0 reposts · 0 replies
Open on X →
@theworldlabs this is like the millionth ai thing called atlas. pls come up with a different name.
18.6K views · 292 likes
· 0 reposts · 4 replies
Open on X →
@theworldlabs Is the AI doing the fluid simulation or was this captured?
1.8K views · 3 likes
· 0 reposts · 2 replies
Open on X →
Atlas is our scalable foundation model that can perceive, generate, reason, and interact with virtual and physical worlds.
We're opening up early access in the coming weeks.
Learn more and sign up here:
https://t.co/SHjFaNWedP
101.2K views · 643 likes
· 33 reposts · 16 replies
Open on X →
All of this is powered by one unified architecture: a multimodal autoregressive diffusion transformer, pretrained from scratch.
This foundation blends the best of modern LLMs and video models, benefiting from the architectural, algorithmic, and systems advances from both areas.
104.5K views · 475 likes
· 25 reposts · 4 replies
Open on X →
0:27
For robotic simulation, Atlas reconstructs a space from just a few photos and generates the photorealistic RGB and depth data any robot's sensors would observe on any trajectory.
Robots can now be trained and tested in far more spaces. Until now, scanning spaces like these http
148.2K views · 602 likes
· 37 reposts · 6 replies
Open on X →
0:55
Atlas also outputs explicit 3D from one to many input images, beating top open source reconstruction models.
Passing more images gives Atlas more context: the more it sees, the less it imagines. https://t.co/5nB2eFC7UQ
142.2K views · 527 likes
· 24 reposts · 7 replies
Open on X →
0:46
Atlas understands both the spatial structure of the world and how it evolves over time.
This lets us turn a handful of ordinary cameras into a "bullet time" multiview capture studio, capturing dynamic moments frozen in time. https://t.co/u8OLTGEfMw
278.9K views · 1.3K likes
· 89 reposts · 22 replies
Open on X →
0:10
We pre-trained Atlas from scratch to take multimodal inputs, including camera movement, and turn it into 3D grounded views.
Atlas puts you in control: direct the views, reconstruct real spaces with your inputs, and build explorable worlds.
Read more:
https://t.co/SHjFaNWedP
319.3K views · 1.1K likes
· 66 reposts · 13 replies
Open on X →
By positioning multiple input views within the model's spatial context, Atlas allows you to generate image and video frames with precise control.
Here, we hand-designed a camera trajectory to generate a 1 minute video at 1440p resolution from seven reference images. https://t.co
251.1K views · 1.1K likes
· 58 reposts · 12 replies
Open on X →
1:00
The next generation of robotics needs models that can understand, simulate, learn from, and act across virtual and physical worlds.
We’re hiring a Sr Business Development Lead, Robotics & Physical AI to help bring this technology into real-world applications 🤖🚀 https://t.co/C1fd
50.4K views · 209 likes
· 15 reposts · 14 replies
Open on X →
Viewing these worlds at full scale on an LED stage is mesmerizing.
From 16K LED volumes to real-time production workflows, here are a few ways Marble is being used in virtual production and VFX ↓ https://t.co/BnQP9hjO00
24.8K views · 140 likes
· 16 reposts · 5 replies
Open on X →
270+ builders joined us in LA for the Worlds in Action Hackathon.
In one weekend, 64 teams built projects ranging from immersive storytelling and mixed reality games to filmmaking tools, tabletop worlds, and audio-reactive experiences.
Check out what they built ↓ https://t.co/x
20K views · 84 likes
· 12 reposts · 8 replies
Open on X →
To scale robot intelligence, we must scale the worlds in which robots learn. 🤖🌎
31.9K views · 78 likes
· 23 reposts · 9 replies
Open on X →
Against accounts of the same size
16 posts from the last 90 days, next to the 100K–1M follower range. shown widely, but few of those viewers react.
Median views37 586this account5 983median for 100K–1M
Reach, %34.19%this account1.49%median for 100K–1M
Engagement, %0.53%this account0.93%median for 100K–1M
| Metric | This account | Median for 100K–1M | Ratio |
|---|---|---|---|
| Median views per post | 37 586 | 5 983 | 6.28× |
| Reach (views ÷ followers) | 34.19% | 1.49% | 22.9× |
| Engagement rate | 0.53% | 0.93% | 0.56× |
Others in this range → Compare with another account → How these benchmarks are built →
Growth & engagement
How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.
Views per post
251.1K1 Sep
319.3K
278.9K
142.2K
148.2K
104.5K
101.2K
1.8K
18.6K
1952 Sep
9K8 Sep
8.6K
3K
755
Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.
Engagement rate per post
0.48%1 Sep
0.38%
0.54%
0.40%
0.44%
0.49%
0.69%
0.29%
1.59%
0.51%2 Sep
0.76%8 Sep
1.29%
1.16%
0.93%
Reactions — likes, reposts, replies and quotes — divided by views. Median for 100K–1M accounts is 0.93%.
What the audience does
Likes72.8%6 835 in total
Reposts4.3%408 in total
Replies1.4%130 in total
Quotes1.3%119 in total
Bookmarks20.2%1 895 in total
Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.
The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.
Similar accounts
Loopify 🧙♂️ ✓
@Loopify
219.9K followers
· 99.6K posts
FREEN OFFICIAL ✓
@freenfanclub_
219.9K followers
· 25.8K posts
Homeland ✓
@SHO_Homeland
219.9K followers
· 9.8K posts
adaa khan ✓
@adaa1nonly
219.9K followers
· 4.3K posts
STM
@stminfo
219.9K followers
· 26.7K posts
Más Vale Tarde
@MVTARDE
219.8K followers
· 75.9K posts
Norwegian Cruise Line
@CruiseNorwegian
219.8K followers
· 34.3K posts
StellarBlade ✓
@StellarBlade
219.8K followers
· 4.9K posts
Frequently asked questions about @theworldlabs
How many followers does @theworldlabs have?
109 943 followers.
How many posts has @theworldlabs published?
560 posts.
How do posts by @theworldlabs perform?
Collected posts: 18. Views: 1 514 516. Likes: 6 835.