Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report Paper • 2608.15763 • Published 14 days ago • 51
Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus Paper • 2608.12149 • Published 24 days ago • 30
Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More Paper • 2502.07490 • Published Feb 11, 2025 • 10
