Search papers, labs, and topics across Lattice.
3
0
7
Achieving oracle-level Bayesian predictions with a multi-task framework that adapts seamlessly to new priors, all while being orders of magnitude faster.
Achieve safe RL exploration from day one without conservative optimization or hyperparameter tuning, by probabilistically regulating a new policy based on a safe reference policy.
PRIMO lets you quantify exactly how much each missing modality hurts your model's predictions, instance by instance.
