Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus
Paper • 2608.12149 • Published • 30
piao ya
piao
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus updated a collection over 1 year ago
11 updated a collection about 2 years ago
11Organizations
upvoted a paper about 2 months ago
updated a
collection over 1 year ago
updated a
collection about 2 years ago
liked a
model almost 3 years ago
liked 2
Spaces about 3 years ago
liked 2
models about 4 years ago
liked a
model over 4 years ago
