KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs 事件

KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs arXiv:2605.29259v1 Announce Type: cross Abstract: Given the wide range of deployment targets, flexible model selection is essential for optimizing performance within a given compute budget. Recent work demonstrates that stitching pretrained models within a model family enables cost-effective interpolation of the accuracy-efficiency tradeoff space. Stitching transforms intermediate activations from one pr