SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space
Paper • 2511.20102 • Published • 28 •
3
🔄 In a Training Loop
Zhenyi Shen
zen-E
AI & ML interests
LLM Reasoning
Recent Activity
updated a model about 1 hour ago
zen-E/qwen25-7b-inst-deepscalar-grpo-200steps-4k published a model about 1 hour ago
zen-E/qwen25-7b-inst-deepscalar-grpo-200steps-4k updated a model about 2 hours ago
zen-E/qwen25-7b-inst-dapo-grpo-200steps-4kOrganizations
None yet
commented a
paper 7 months ago