An empirical study examines why World Action Models (WAMs) generalize, comparing Explicit WAMs, which denoise future frames into clean video alongside every action chunk during inference, against Latent WAMs, which avoid that video-denoising cost. The work addresses the disputed question of whether future frames must be generated at inference time given the heavy computation cost of video denoising.
World action models (WAMs) predict the future alongside actions during training. Due to the heavy computation cost of video denoising, whether the future must still be generated during inference is disputed: Explicit WAMs denoise it into clean frames along with every action chunk, whereas Latent WAM
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.