Search papers, labs, and topics across Lattice.
Affiliation:
5
0
6
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.
Online critic backpropagation for flow-based robot policies is completely unnecessary: amortizing trajectory-aware adjoint costates into a lightweight network achieves superior value alignment at 3.6× the speed.
Achieving high-fidelity motion control in video diffusion transformers without any training or extensive prompt engineering could revolutionize how we generate dynamic video content.
MTL may boost meaning recognition in L2 speech tasks, but it can severely compromise transcription accuracy, especially in English.
Dramatically improve ultra-low field MRI image quality by leveraging diffusion-guided distribution matching and anatomical priors in an unpaired translation framework.
