Search papers, labs, and topics across Lattice.
3
0
5
0
RLDX-1 achieves double the success rate of existing VLAs on complex humanoid tasks, suggesting a leap in robots' ability to handle contact-rich, dynamic manipulation.
Forget dense pose targets: sparse taxonomy guidance unlocks dexterous manipulation with surprising generalization and controllability.
Correcting for suboptimal behavior during preference learning unlocks substantial gains in offline RLHF and improves online performance in continuous control tasks.
