Search papers, labs, and topics across Lattice.
Affiliation:
2
0
2
Physics engines do not need to be replaced by black-box neural networks鈥攑atching them with Bayesian-inferred code enables robots to actively discover missing physical mechanisms with drastically fewer real-world interactions.
Current AUC metrics can mislead deepfake detector evaluations, but Cross-AUC reveals the true impact of domain shifts on performance.
