Search papers, labs, and topics across Lattice.
2
0
2
Discarded tail actions in chunked robot policies remain faithful to counterfactual replans until action velocity fluctuates, allowing policies to safely extend execution horizons and slash inference calls by up to 1.7× at zero extra cost.
By injecting alignment guidance directly into the diffusion model's score function, AGSM avoids the pitfalls of contrastive learning and generates images with improved counting accuracy and semantic fidelity.
