(d) RePercENT Figure 10: (M = 2) Pairwise confusion matrices for the synthetic setting wit(d) RePercENT Figure 10: (M = 2) Pairwise confusion matrices for the synthetic setting with two modalities, shown for MLP, GRU, gMLP, and RePercENT. While all models largely separate unique and shared information, sequence-aware models yield stronger intra-component accuracy, as reflected by higher main-diagonal values.这张图/表用于判断 RePercENT 的实验收益来自哪里。重点看替换、消融或跨模型设置下趋势是否一致，而不是只看单个最高分。(a) gMLP (b) RePercENT Figure 15: (M = 5) Pairwise confusion matrices for the synthetic se(a) gMLP (b) RePercENT Figure 15: (M = 5) Pairwise confusion matrices for the synthetic setting with five modalities, shown for gMLP, and RePercENT. Despite the increased number of modality pairs, both models successfully encode pairwise unique and shared representations, yielding similar disentanglement performance.这张图/表用于判断 RePercENT 的实验收益来自哪里。重点看替换、消融或跨模型设置下趋势是否一致，而不是只看单个最高分。
