ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads Paper • 2608.02703 • Published 4 days ago • 5
Selectivity and Shape in the Design of Forward-Forward Goodness Functions Paper • 2604.13081 • Published Apr 16
Diffutron: A Masked Diffusion Language Model for Turkish Language Paper • 2603.20466 • Published Mar 20 • 9
Diffutron: A Masked Diffusion Language Model for Turkish Language Paper • 2603.20466 • Published Mar 20 • 9