arXiv cs.AI / cs.LG / cs.CL·15d agoSAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking#attention-sparsification#efficiency#flashattentionAI research2
arXiv cs.AI / cs.LG / cs.CL·15d agoAttention Quantization for Tabular Foundation Models#fp8#inference-efficiency#quantizationAI research1
Hugging Face daily papers·16d agoSAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking#attention#efficiency#long-context1
