Check out this shiny new, fast and dynamic web renderer for 3D Gaussian Splats! The things one could do are just mind boggling! So proud of the World Labs team that made this happen, and we are making this open source for everyone!

We're sharing a VR demo that lets you step into generated 3D worlds on Quest3 and Vision Pro: lofiworlds.ai This is just the beginning! You've seen lots of generated images and videos. 3D worlds are next, and we're building them at World Labs

10 years ago, deep learning was in its infancy. PyTorch didn't exist. Language models were recurrent, and not large. But it felt important: a new technology that would change everything. That's why Fei-Fei Li , Andrej Karpathy, and I started CS231N Staff back in 2015 - to teach the world's

CS231N Staff turned 10 this spring! Thrilled to co-teach with this all-star crew, Fei-Fei Li, Justin Johnson, & Zane Durante! We’ve got an updated syllabus & brand-new, exciting assignments. Lectures are now live on YouTube, go binge the classics and the new hits! youtube.com/playlist?list=…

We can generate some pretty big worlds now - all in persistent 3D that you can explore for as long as you want

Generated 3D worlds aren't just for viewing, you can also play projectile jenga inside link below

I reimagined my living room with World Labs. Gemini helped design it, World Labs generated the 3D environment, and VPS localized it to my space 1:1 scale. I can now step into a persistent redesign in mixed reality and explore it as though it exists physically. How it was built:

We're excited to see so many of you creating new worlds in our Marble beta preview! Here's a tour through some of your latest creations… To join the fun, sign up at worldlabs.ai/waitlist — we're letting in new users as fast as we can 🔥

Morning stroll into a World Labs portal. I picture a future where you describe your environment and it instantly materializes around you.

Are you an expert in diffusion models? Want to work with an amazing team building the next generation of world models World Labs ? We are hiring!

We are sharing a research preview of our latest model from World Labs! RTFM is an autoregressive diffusion transformer trained on large-scale video data. It generates video frames in real-time without building an explicit 3D model of the world. Try the demo today!

We're hiring!! Come build more frame models with us!🖼️🎮⚡️👇 jobs.ashbyhq.com/worldlabs

Today we announced RTFM (Real-Time Frame Model) — a world model that generates frames in real time from any camera viewpoint. Unlike standard video models, RTFM understands 3D geometry. You can literally move the camera through the generated world. 🎥👇

real-time WebAR experience + 5MB gaussian splat. Generated this scene from a photo using World Labs.

"Tensor Parallel" is a terrible name ... all parallelization strategies parallelize tensors somehow. It would be better to call it "channel parallel" = CP, but that conflicts with "context parallel". Maybe "feature parallel" = FP?