Track manipulation, locomotion and embodied systems.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
0
Aerial VLN agents can achieve over 74% success by learning to execute full action chunks and stop accurately, drastically reducing inference costs and overcoming the 47% no-stop failure rate of standard behavior cloning.
Unlocking accurate reactive dynamics in energetic materials with MLPs trained on a mere 13,680 configurations by integrating a novel spherical-harmonic basis and knowledge-guided active learning.