Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds 事件

Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds arXiv:2510.27391v2 Announce Type: replace Abstract: Modality alignment is critical for vision-language models (VLMs) to effectively integrate information across modalities. However, existing methods extract hierarchical features from text while representing each image with a single feature, leading to asymmetric and suboptimal alignment. To address this, we propose Alignment across Trees, a method that constructs and aligns t