Search papers, labs, and topics across Lattice.
3
0
7
IMLE-VLA is introduced, which replaces the iterative action head with a single-step conditional generator trained via conditional Implicit Maximum Likelihood Estimation (cIMLE), and promotes multimodal action coverage, avoiding the mode collapse of naive regression heads while eliminating multi-step sampling entirely.
Point-based neural editing can now adapt to large deformations without ground truth images, achieving superior consistency and fewer artifacts.
By weighting model rollouts based on predicted confidence, WIMLE achieves state-of-the-art sample efficiency in model-based RL, outperforming existing methods on complex continuous control tasks.
