Residual Stream Duality in Modern Transformer Architectures Paper • 2603.16039 • Published about 1 month ago • 4
Residual Stream Duality in Modern Transformer Architectures Paper • 2603.16039 • Published about 1 month ago • 4
Language Server CLI Empowers Language Agents with Process Rewards Paper • 2510.22907 • Published Oct 27, 2025 • 5
Robust Layerwise Scaling Rules by Proper Weight Decay Tuning Paper • 2510.15262 • Published Oct 17, 2025 • 6