AI RESEARCH
Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Language Models through Latent Semantic Alignment
arXiv CS.LG
•
ArXi:2510.24208v2 Announce Type: replace-cross Language Models (LMs) encode substantial knowledge in their parameters, yet it remains unclear how to transfer such knowledge in a fine-grained manner, namely parametric knowledge transfer (PKT). A central challenge is to make cross-scale transfer effective and efficient when source and target models differ in architecture and parameterization, making direct parameter reuse strongly limited by neural incompatibility. In this paper, we identify latent semantic alignment as the key prerequisite for cross-scale knowledge transfer.