Weak-SIGReg: Covariance Regularization for Stable Deep Learning Paper • 2603.05924 • Published Mar 6 • 2
ATMA: Length-Invariant Language Modeling via Polar Attention and Gated-Delta Compression Memory Paper • 2606.25156 • Published 16 days ago • 2
ATMA: Length-Invariant Language Modeling via Polar Attention and Gated-Delta Compression Memory Paper • 2606.25156 • Published 16 days ago • 2