Search papers, labs, and topics across Lattice.
University of Luxembourg
3
0
4
Geometry-guided width allocation in Transformers can lead to substantial improvements in model performance, reducing validation loss more effectively than traditional methods.
Retaining only the tangential component of the feed-forward network can preserve model quality while enhancing prediction accuracy in Transformer dynamics.
Drifting Models get a friction boost: DMF matches or beats Optimal Flow Matching on FFHQ image translation while slashing training compute by 16x.
