标签
This paper introduces low interaction rank as a unified theoretical framework for multiplicative dual-encoder networks, covering approximation, sample complexity, normalization, and identifiability, with experiments on operator learning and CLIP models.
本文提出ConRetroBert，一种用于基于模板的单步逆合成的双编码器框架，使用对比预训练和列表排序来提高模板预测准确性，在USPTO-50k基准上达到最高75.4%的top-1准确率，同时保持可解释性。