Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT 文章

ArXiv CS.AI2026-07-29PAPERen作者: Cen Lu, Yung-Chen Tang, Andrea Cavallaro
查看原文 →
关系图谱

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT · 相关公司

暂无数据