Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design

ArXi:2507.15336v3 Announce Type: replace-cross Designing high-performance neural networks for new tasks requires balancing optimization quality with search efficiency. Current methods fail to achieve this balance: neural architectural search is computationally expensive, while model retrieval often yields suboptimal static checkpoints. To resolve this dilemma, we model the performance gains induced by fine-grained architectural modifications as edit-effect evidence and build evidence graphs from prior tasks.