Search papers, labs, and topics across Lattice.
3
0
5
2
InvLT achieves superior calibration performance without compromising classification accuracy or increasing parameter complexity, setting a new standard for post-hoc uncertainty calibration.
Guaranteeing injectivity in autoencoders unlocks more robust and geometrically faithful dimensionality reduction, even under distribution shift.
DNNs can be both more accurate *and* better calibrated: Generative Cross-Entropy (GCE) offers a way to escape the accuracy-calibration trade-off.
