Mohamed El Banani

@_mbanani

MTS @theworldlabs. Prev: @UMichCSE, @GoogleAI, @MetaAI, @GeorgiaTech. I am interested in computer vision, machine learning, and cognitive science. 🇪🇬

San Francisco, CA

mbanani.github.io

Replies Reposts Media

Pinned
Mohamed El Banani
@_mbanani
Dec 2, 2024
We’re finally sharing what we’ve been up to @theworldlabs! This is the first step on our journey to build fully interactive and immersive worlds that allow you to bring your creativity to life. Check out the demos, my favorites are the Kandinsky landscape and Van Gogh terrace.
World Labs
@theworldlabs
Dec 2, 2024
We’ve been busy building an AI system to generate 3D worlds from a single image. Check out some early results on our site, where you can interact with our scenes directly in the browser! worldlabs.ai/blog 1/n
00:00
1
Mohamed El Banani
@_mbanani
Sep 1
Very excited that I can finally share what we’ve been working on! Atlas is a big step towards fully interactive and controllable world models. Can’t wait to see what you all build with Atlas!!
World Labs
@theworldlabs
Sep 1
Introducing Atlas: The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D. Model the world, move the camera, and simulate space & time.
00:00
6
Mohamed El Banani
@_mbanani
Oct 17, 2025
We've been exploring different ways of modeling the world at @theworldlabs. This direction combines our real-time learned renderer with posed frames as a persistent spatial memory. I am excited to see where we go next! Check out the demo here: rtfm.worldlabs.ai
World Labs
@theworldlabs
Oct 16, 2025
Introducing RTFM (Real-Time Frame Model): a highly efficient World Model that generates video frames in real time as you interact with it, powered by a single H100 GPU. RTFM renders persistent and 3D consistent worlds, both real and imaginary. Try our demo of RTFM today!
00:00
2
Mohamed El Banani
@_mbanani
Apr 5, 2023
Language models keep getting better, can we use them for better visual learning? In our CVPR paper, we use language models to sample conceptually similar and visually dissimilar image pairs! We use those pairs for stronger contrastive learning. 🧵⬇️
Justin Johnson and 2 others
2
Mohamed El Banani
@_mbanani
Oct 14, 2021
Check out "Bootstrap your own correspondences" w/ @jcjohnss at #ICCV2021 (session 5). Come to the Q&A session to chat with me about self-supervised geometric feature learning and registration. ⏰ October 14th: 9-10am EDT 🌐 mbanani.github.io/byoc 📽️ youtu.be/YJ9oTyI0xF0
1