CORTEXEnables Visual Planning Ability
While the Conditional Diffusion Transformer (CDiT) from Navigation World Models uses simple control signals like velocity and rotation, modeling whole-body human motion presents greater challenges. Human actions are high-dimensional, temporally extended, and physically constrained. To address these challenges, we extend the CDiT method in three ways: Random Timeskips: Allows the model to learn both short-term motion dynamics and longer-term activity patterns. Sequence-Level Training: Models en
11 juil.