Tag
SpecMRL 提出在参数化谱空间中重新组织特征以改进嵌入的前缀读出，在 MTEB 上以更少的嵌入维度超越标准 MRL 及其全维表现。
Dylan Castillo compares Matryoshka Representation Learning (MRL) with Principal Component Analysis (PCA) for reducing embedding dimensions, running experiments across eight BEIR datasets to evaluate retrieval quality versus vector size reduction.