AI RESEARCH
KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs
arXiv CS.AI
•
ArXi:2605.29259v1 Announce Type: cross Given the wide range of deployment targets, flexible model selection is essential for optimizing performance within a given compute budget. Recent work nstrates that stitching pretrained models within a model family enables cost-effective interpolation of the accuracy-efficiency tradeoff space. Stitching transforms intermediate activations from one pretrained model into another, producing a new interpolated stitched network. Such networks provide a pool of deployment options along the accuracy-efficiency spectrum.