Search papers, labs, and topics across Lattice.
Affiliation:
4
0
7
3
Sampling-Guided Policy Search (SGPS), which couples recurring action-target refinement by sampling-based model-predictive control with first-order policy optimization with first-order policy optimization, and shows that refinement improves policy learning beyond initialization and tracking alone.
The Decoupled Embodiment Model (DEM), which pairs a fine-tuned DINOv3 encoder and a frozen NeoBERT encoder with a MeanFlow head that generates each action chunk in a single forward pass, achieves observed success comparable to state-of-the-art VLM-backbone policies under the evaluation protocol.
Task-conditioned foveated perception can drastically enhance the robustness and efficiency of robotic foundation models by aligning policy learning with relevant visual evidence.
Visual RL training can be sped up by orders of magnitude using trajectory perturbations, achieving state-of-the-art results on MuJoCo with just a single RTX 4080.
