Search papers, labs, and topics across Lattice.
CISPA Helmholtz Center for Information Security
4
0
6
Bypassing traditional model training, MASHT achieves state-of-the-art time series classification by harnessing the power of pretrained tabular foundation models.
Structural biases can be identified through dependent mechanism shifts, revealing hidden confounding and selection biases that traditional methods miss.
Uncover hidden drivers of disparity: pinpoint the specific combinations of characteristics that explain outcome gaps between populations.
Ditch the restrictive assumptions: Sysurv uses differentiable random survival forests to automatically discover interpretable subgroups with exceptional survival rates.