arXiv:2605. 13894v2 Announce Type: replace-cross Abstract: In this work, we introduce a Tropical Axial Attention neural reasoning architecture that replaces vanilla softmax dot-product attention with max-plus operators, inducing a piecewise-linear structure aligned with dynamic programming formulations.
arXiv:2608. 04460v1 Announce Type: cross Abstract: The quantitative analysis of 3D neuronal morphologies requires capturing both graph topology and spatial geometry.
arXiv:2607. 18311v1 Announce Type: cross Abstract: Comparing phylogenetic tree topologies is essential for understanding epidemic dynamics, yet biologically meaningful distances such as the Subtree Prune and Regraft (SPR) distance are NP-hard to compute and intractable on large datasets.
arXiv:2310.08774v3 Announce Type: replace-cross Abstract: Phylogenetics is a branch of computational biology that studies the evolutionary relationships among biological entities. Its long history an...
arXiv:2606. 11646v1 Announce Type: new Abstract: Compositional data -- vectors encoding relative proportions -- arise across scientific domains, including ecology, geochemistry, and genomics.
arXiv:2606. 25989v1 Announce Type: cross Abstract: Automated classification of marine species from underwater imagery is essential for scalable ocean biodiversity monitoring and conservation policy.
Compositional data -- vectors encoding relative proportions -- arise across scientific domains, including ecology, geochemistry, and genomics. The features in these data often come with known hierarchical structure (e.
The paper investigates why hierarchical image retrieval improves when using frozen DINOv2 features. It compares Euclidean and hyperbolic embeddings trained with taxonomy-distance regression or a taxonomy-aware supervised contrastive objective, finding that the choice of loss function (objective family) contributes more to hierarchy-aware performance than the geometry of the embedding space. Semantic alignment of the taxonomy also plays a significant role, while stronger negative curvature does not explain the gains.
arXiv:2608. 15402v1 Announce Type: new Abstract: Generative model alignment has received broad interest, and significant progress has been made in supervised fine-tuning and inference-time computation.
arXiv:2607. 02909v1 Announce Type: cross Abstract: Taxonomies provide key information about the semantic relationships between concepts and the inherent organization of vision and language.
arXiv:2602. 01893v2 Announce Type: replace-cross Abstract: We present a geometric framework for analysing multi-head attention in large language models (LLMs).
arXiv:2606. 07690v1 Announce Type: cross Abstract: Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repeatedly finetuning models.
arXiv:2606. 24995v1 Announce Type: new Abstract: Tabular foundation models (TFMs) achieve strong performance on microbiome abundance data, yet their robustness under realistic distribution shift remains poorly characterized.