Search papers, labs, and topics across Lattice.
Affiliation:
4
0
4
CueNav is presented, a video model-based navigation framework combining visual cue guided video planning with an embodiment-specific Inverse-Dynamics Model (IDM) that paves the way toward a generalizable navigation framework for longer-horizon planning and embodiment-aware control.
Optimal learning rates for training massive Mixture-of-Experts models can be accurately predicted from small proxy models, achieving high fidelity even at trillion-token scales.
