WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation Paper • 2608.24479 • Published Aug 25 • 139
Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus Paper • 2608.12149 • Published Aug 12 • 30
view article Article Harness, Scaffold, and the AI Agent Terms Worth Getting Right sergiopaniego, ariG23498 • May 25 • 148
ModernBERT-TR Collection A 150M-parameter Turkish encoder family of base and downstream task models. • 20 items • Updated Jul 20 • 13