Search papers, labs, and topics across Lattice.
3
0
6
0
MachEmbodied-U0, a unified embodied foundation model connecting understanding and generation experts through a Mixture-of-Transformers architecture, is presented, a unified embodied foundation model connecting understanding and generation experts through a Mixture-of-Transformers architecture that combines competitive downstream control performance with transferable task-grounding and visual-dynamic capabilities across simulation and the real world.
Ditch the optimization: MoRe achieves real-time 4D scene reconstruction from monocular video using a feedforward transformer that disentangles motion and structure.
By disentangling structure and motion in the latent space, CoWVLA achieves superior visuomotor learning compared to standard world-model and latent-action approaches.
