@theworldlabs profile picture
World Labs @theworldlabs

World Labs is a spatial intelligence company, building frontier models that can perceive, generate, and interact with the 3D world.

Joined January 2024
  • Posts 488
  • Following 49
  • Followers 71,255
100 Photos and videos
Pinned Post
World Labs
@theworldlabs
Apr 7
We're excited to be rolling out two model updates today! Marble 1.1: Improves lighting and contrast, with a major reduction in visual artifacts. Marble 1.1-Plus: Our new model built for scale. Create larger, more complex environments than ever before.
0:37
47
176
1,275
216,153
Join us at Worlds in Action Hackathon during SIGGRAPH 2026! From multiplayer games to immersive interactive experiences, here's a look at what's possible with Marble across Unity, Unreal Engine, and the web with three.js Los Angeles • July 18–19
0:34
10
24
183
38,859
We're excited to team up with @SensAIHackademy and @XGRIDS_OFFICIAL for the Worlds in Action Hackathon at SIGGRAPH 2026. Register here: luma.com/u7pmhw92 Shoutout to the builders featured above: @cglewis92 @mattworkman @BrittaniNatali @XRarchitect

Worlds in Action Hack [02-LA]: SIGGRAPH EDITION · Luma

World Model & GenAI Hackathon Two days to build the future of interactive AI worlds. Right before #SIGGRAPH2026, founders, researchers, engineers, VFX artists,…

luma.com
1
13
1,744
Worlds in Action Hackathon is coming to SIGGRAPH 2026! 📍 Los Angeles 📅 July 18–19 Join us for two days of building with world models for gaming, VFX, AR/VR, interactive experiences, and more. Details below ↓
0:13
6
27
143
15,824
We're excited to partner with @SensAIHackademy to bring Worlds in Action Hackathon to SIGGRAPH 2026. More details: • Marble Pro access for every team • Online Workshops and pre-hack networking • $2,000 in credits for winning teams Register here: luma.com/u7pmhw92

Worlds in Action Hack [02-LA]: SIGGRAPH EDITION · Luma

World Model & GenAI Hackathon Two days to build the future of interactive AI worlds. Right before #SIGGRAPH2026, founders, researchers, engineers, VFX artists,…

luma.com
4
13
2,046
From Marble to Unreal Engine. Learn how to bring Marble-generated splats into @UnrealEngine using the VIVE Mars Nova 3DGS Plugin, including collision setup, environment lighting, and scene configuration. Watch here ↓
0:13
4
28
158
15,574
Created for the World Labs community by @cglewis92. youtu.be/PS8_s43XYkw

How to Import Gaussian Splats into Unreal Engine with the VIVE Mars...

Learn how to bring Marble-generated scenes into Unreal Engine using...

youtube.com
8
3,669
World Labs reposted
Brittani Natali
@BrittaniNatali
Jun 16
One of my favorite things about gaussian splats is how quickly a few images can become something you can explore. This environment was stitched together from three images using @theworldlabs Breakdown below ↓
0:16
6
17
136
13,008
The future of AI should be grounded in human agency, creativity, and understanding. @FastCompany explores the rise of world models and features insights from World Labs cofounder @drfeifei: "Her vision for World Labs—and its human-centered future—is both consistent and persistent. It's like a simulation in her world model. Once in place, it stays put." Read the full article here ↓
Fast Company
@FastCompany
Jun 15
“I’m keenly aware of multiple clocks,” Li says. “They’re all ticking.” f-st.co/oOa5Sp3
7
57
298
60,153
Today we are sharing three new research papers, each exploring a new way to generate 3D content by leveraging large-scale generative models and 2D priors. These projects were led by our incredible interns @HaoZhang623 @BDuisterhof @DrTunnels [1/4]
1:05
16
93
661
114,480
Modality Forcing adapts text-to-image models to reason jointly about text, images, and depth. It shows that text-to-image is a scalable pretraining objective for 3D reasoning, and how text-to-RGBD, depth estimation, and depth-to-image can be unified in a single model. [3/4] x.com/BDuisterhof/status/206…
Bardienus Duisterhof
@BDuisterhof
Jun 12
Introducing Modality Forcing, a recipe for post-training T2I models for SOTA RGB-Depth generation! Text-to-image (T2I) models learn rich representations of the spatial world. How do we build on this prior for high-quality depth generation? modality-forcing.github.io 🧵 [1/6]
0:26
2
1
37
7,492
Flex4DHuman lifts monocular video into dynamic 4D Gaussians. A video diffusion model is finetuned to generate synchronized multiview videos which are distilled into 4D Gaussians. With this method, a video of a person dancing can be lifted to 4D and composted into a 3D world. x.com/DrTunnels/status/20654…
Andy Cheng@DrTunnels
Jun 12
Introducing Flex4DHuman: a video diffusion model that turns a single video or sparse camera views into synchronized multi-view videos using camera-pose and text conditioning. The generated views can be reconstructed into 4D Gaussian splats for AR/VR, gaming, and video reshooting. 🌐andy-cheng.github.io/Flex4DH… [1/4]
1:42
1
38
5,254
Millions of Gaussian splats, rendered directly in the browser. For ICARE, the creative team designed and iterated 7 worlds with Marble, then streamed them in real time using Spark 2.0 and Three.js Here's how the pipeline works ↓🧵
3:05
2
17
101
12,051
One of the more interesting parts of the pipeline was the trailer itself. Rather than rebuilding scenes for a separate cinematic workflow, the team connected Blender directly to the live Spark 2.0 runtime and animated cameras in the same worlds used for gameplay. more in the launch post here: x.com/theworldlabs/status/20…
World Labs
@theworldlabs
Jun 9
We turned dreams into worlds. Then filled them with history's greatest minds. Not a video. A world, running directly in your browser. Step inside ↓
0:40
1
7
3,838
ICARE is an early example of what's possible when world models become part of the creative workflow, helping teams rapidly create, iterate on, and connect interactive experiences. Play it now: icare-game.world/

Icare

Talk to dreamers, collect artifacts, restore each world, and recover your lost feathers. Powered by SparkJS.

icare-game.world
9
1,640
We turned dreams into worlds. Then filled them with history's greatest minds. Not a video. A world, running directly in your browser. Step inside ↓
0:40
11
35
226
70,362
A glimpse behind the scenes. The launch video wasn't rendered separately. The team connected Blender to the live Spark 2.0 runtime, animating cameras and previewing the splat-rendered result in real time. The same Marble gameplay worlds also helped create the launch video.
0:54
1
19
2,450
Later this week we'll share a deeper look at the workflows behind ICARE: • World generation and design • Browser-native splat streaming • Gameplay and interaction systems • AI-assisted production Marble • @sparkjsdev • @threejs • @Blender
0:20
1
21
2,286
Load more