OWL Logo
    OWL
    HomeProjectsTeamContributeBlogContact
    OWL Logo
    OWL
    Sign in

    Built by OWL

    •Privacy Policy•Terms of Use

    OWL Blog

    Stay updated with our latest developments and research findings.

    Why Human Evaluation is the Missing Piece in World Model Development
    August 1, 2025

    Why Human Evaluation is the Missing Piece in World Model Development

    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.

    Optimizing Diffusion Decoders with Depth Pruning (Using ODE Regression)
    July 27, 2025

    Optimizing Diffusion Decoders with Depth Pruning (Using ODE Regression)

    We show applying ODE regression to drastically reduce the depth of our diffusion decoder, leading to a 40x speedup!

    Product of Experts for Visual Generation - An Illustrated Example
    July 12, 2025

    Product of Experts for Visual Generation - An Illustrated Example

    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!

    Fast Audio Video World Models: Part 2
    July 2, 2025

    Fast Audio Video World Models: Part 2

    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

    Generation vs. Reconstruction: Striking A Balance
    June 21, 2025

    Generation vs. Reconstruction: Striking A Balance

    The generation vs reconstruction trade-off gets weird when you push compression. Learn more about how we're managing it in this blog post!

    Fast Audio Video World Models: Attempt 1
    June 13, 2025

    Fast Audio Video World Models: Attempt 1

    Autoencoders for Diffusion: A Deep Dive
    June 7, 2025

    Autoencoders for Diffusion: A Deep Dive

    Join us as we try to figure out how to make a good custom autoencoder for our World Model.

    Towards an Even Larger Video Game Dataset: Inverse Dynamics Models For Bootstrapping Unlabelled Data
    May 30, 2025

    Towards an Even Larger Video Game Dataset: Inverse Dynamics Models For Bootstrapping Unlabelled Data

    This week we set our sights on taming unlabeled internet data for World Model training.

    Towards a Large Open Video Game Dataset
    May 23, 2025

    Towards a Large Open Video Game Dataset

    Today we are marking the start of our journey towards a general purpose open source video game world model.