Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
TECOgithub.com · Low evidenceTECO is a vector quantized latent dynamics video prediction model that uses a MaskGit prior to generate long, temporally consistent videos. It outperforms state-of-the-art baselines on benchmarks including DMLab, Minecraft, and Kinetics 600 by efficiently conditioning on hundreds of frames during training and generation.
Parse Score