Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 5 days ago • 213
One Proposal for Every Margin: Zero-Shot Amortized Sequential Importance Sampling for Binary Matrices Paper • 2609.35514 • Published 3 days ago • 4
PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers Paper • 2609.32429 • Published 5 days ago • 5
Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss Paper • 2609.33620 • Published 4 days ago • 5