Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus Paper • 2608.12149 • Published 4 days ago • 19 • 4
Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus Paper • 2608.12149 • Published 4 days ago • 19
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published 6 days ago • 331
Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification Paper • 2607.24027 • Published 20 days ago • 37