Stay updated with our latest developments and research findings.
We're releasing OWL Eval, the first open-source evaluation platform built specifically for studying how humans perceive AI-generated videos. After running studies with hundreds of participants, we've learned that human evaluation reveals critical model failures that automated metrics completely miss. Our platform makes it dead simple to run these studies at scale.
We show applying ODE regression to drastically reduce the depth of our diffusion decoder, leading to a 40x speedup!
In this blog post, we illustrate a paper that leverages multiple specialist models and incorporating their individual expertise by having them influence the diffusion sampling at inference time. We also provide code examples, visualizations, and intuitions!
We trained an autoencoder with depth maps in the latent. It resulted in far better depth consistency in downstream generations. Next we’re training with optical flow as well, and solving the KV cache problem
The generation vs reconstruction trade-off gets weird when you push compression. Learn more about how we're managing it in this blog post!
Join us as we try to figure out how to make a good custom autoencoder for our World Model.
This week we set our sights on taming unlabeled internet data for World Model training.
Today we are marking the start of our journey towards a general purpose open source video game world model.