@haodongli00
Video world models shouldn't just render plausible pixels, they should understand "how the world evolves". 🤔 Introducing Latent Dynamics Reasoning (LDR). Instead of predicting future frames directly, LDR maps past frames into structured latent states, then rolls those states forward through kinematic integration. It learns only the higher-order motion residuals that drive the rollout. 🚀 To our knowledge, LDR is the first video world model to extrapolate learned dynamics beyond its training distribution. 💪 Paper / code / models / data are now public, check them out! 🥳 - Paper: https://t.co/Mnh1sD9jLf - Code: https://t.co/uJhu28darp - Model: https://t.co/1fJLmwFwTL - Data: https://t.co/Pxl0eirIgo