GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity Paper • 2607.00152 • Published 6 days ago • 5
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity Paper • 2607.00152 • Published 6 days ago • 5
When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling Paper • 2606.28661 • Published 9 days ago • 4
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity Paper • 2607.00152 • Published 6 days ago • 5
When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling Paper • 2606.28661 • Published 9 days ago • 4
When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling Paper • 2606.28661 • Published 9 days ago • 4
Machine Learning vs Deep Learning: The Generalization Problem Paper • 2403.01621 • Published Mar 3, 2024 • 1
No 3D Matrices: A Unified Tensor-Product View of Matrix-Free Cartesian PDE Solvers Paper • 2606.25148 • Published 13 days ago • 1
No 3D Matrices: A Unified Tensor-Product View of Matrix-Free Cartesian PDE Solvers Paper • 2606.25148 • Published 13 days ago • 1
Machine Learning vs Deep Learning: The Generalization Problem Paper • 2403.01621 • Published Mar 3, 2024 • 1
Solve for the Hyperparameter, Skip the Search: Kolmogorov-Optimal Scaling Laws for Spline Regression Paper • 2606.23575 • Published 14 days ago • 1
Solve for the Hyperparameter, Skip the Search: Kolmogorov-Optimal Scaling Laws for Spline Regression Paper • 2606.23575 • Published 14 days ago • 1