Search papers, labs, and topics across Lattice.
UE, Great Britain 6 School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1
3
0
5
0
Reconstructing screen content from a distance is now possible with higher fidelity and robustness, thanks to a new physically-guided deep learning approach that overcomes key instabilities in optical projection.
LoRA in differentially private federated learning gets a 16% accuracy boost with LA-LoRA, which mitigates gradient coupling and noise amplification.
AdamW, a popular optimizer for large models, can now be used in differentially private federated learning without sacrificing convergence speed or accuracy, thanks to a new bias-corrected and variance-stabilized variant.
