Unverified50% confidenceFactExact time
MASA (Matrix Approximation Sparse Attention) uses a closed-form solution score to measure the extent to which each sparse unit can reduce the approximation error of the matrix product.
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe paper reformulates sparse attention as a matrix approximation problem rather than a problem of selecting the largest values from a bag of entries.70% similarUnverified分组量化将权重矩阵按固定大小（通常32或64个元素）分组，每组独立计算量化缩放因子以减少精度损失68% similarUnverifiedRANSAC repeatedly samples minimal point sets at random to estimate a transformation model, classifying points consistent with the model as inliers, and can still reliably estimate a homography matrix when a large number of mismatches are present68% similarVerifiedLoRA decomposes the weight update matrix ΔW into the product of two small matrices A and B whose ranks are much lower than the original matrix, reducing parameter count to as little as one ten-thousandth of the original or even less.67% similarUnverifiedExperiments with MASA across multiple sparse attention methods, multiple benchmarks, and different LLM backbone models show consistent accuracy improvements.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990372API
curl https://kongchang.com/api/v1/knowledge/claims/990372MCP
get_claim(id=990372)