Building frontier world models.
We are Genmo—a research lab dedicated to unlocking the right brain of artificial general intelligence through state-of-the-art world models.
About Us
Our video generation models act as world simulators, driving breakthroughs in embodied AI by enabling infinite explorations in synthetic realities. Video is the ultimate medium for human-AI interaction, seamlessly integrating text, audio, images, and 3D into one unified experience.
Mochi 1, our first public open-source release, is licensed under Apache 2.0 for both individual and commercial use.
Our team includes the original creators of foundational AI research.
Denoising Diffusion Probabilistic Models
DreamFusion: Text-to-3D using 2D Diffusion
Dual Diffusion Implicit Bridges for Image-to-Image Translation
Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization
Video Prediction Models as Rewards for Reinforcement Learning
New Insights on Reducing Abrupt Representation Change in Online Continual Learning
Analysis of Attention in Video Diffusion Transformers
Investors & Advisors
Ion Stoica
UC Berkeley, Databricks Co-Founder
Pieter Abbeel
UC Berkeley, Deep RL pioneer, Covariant AI
Joseph Gonzalez
UC Berkeley, SysML pioneer
Abhay Parasnis
CEO of Typeface
Amjad Masad
CEO of Replit
Sabrina Hahn
Investor and author
Bonita Stewart
BAG, long time executive at Google
Michele Catasta
VP of AI at Replit
Many more