Newest papers

Compositionality with Primitives: A Unified View from Euclidean to Hyperbolic Vision-Language Models

Puru Vaish, Meelad Dashti, Christoph Brüne, Pascal Mettes, Tatiana Tommasi, Nicola Strisciuglio · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29811 · cited by 0 works (OpenAlex) · open-access PDF

Korean

코드 제로 샷 학습 (CZSL)은 이전에 관찰 된 개체 및 특성의 새로운 조합을 인식하는 것을 목표로합니다. 이전의 작업은 대규모 시각 언어 모델이 일반화를 가능하게 할 수있는 분해 할 수있는 의미적 구조를 코딩한다는 것을 보여주었습니다. Geodesically Decomposable Embeddings (GDE) 프레임은 이전에 관찰 된 개체와 특성의 명확한 공간에있는 방향을 식별함으로써 이것을 공식화합니다. 원시적 시각 개념을 인코딩하는 Frechet 중간 배포의 방향을 식별합니다. 보이지 않는 특성 - 객체 조성은 이러한 원시적 인물의 벡터 추가를 통해 합성 될 수 있습니다. 우리는 컴포지션 일반화가 명확한 특성 - 객체 쌍 재

Machine translation (Meta M2M100); the English original follows.

Abstract

Compositional zero-shot learning (CZSL) aims to recognize novel combinations of previously observed objects and attributes. Prior work showed that large-scale vision-language models encode decomposable semantic structures that can be recomposed to enable generalization. The Geodesically Decomposable Embeddings (GDE) framework formalizes this by identifying directions in the tangent space at the Frechet mean of the embedding distribution, which encode primitive visual concepts. Unseen attribute-object compositions can be synthesized through vector addition of these primitives. We revisit the assumption that compositional generalization requires explicit attribute-object pair re-composition. By means of new compositional scoring functions and extensive evaluations, we show that directly using the decomposed primitives suffices for recognizing unseen compositions. In that, we gain insights on how the geometry of the embedding manifold (Euclidean, spherical, or hyperbolic) and dataset structure affect compositional reasoning. Across models (CLIP, DINOv2, MERU, HyCoCLIP), we show that compositional structure consistently emerges as primitive representations, enabling inference on CZSL benchmarks (MIT-States, VAW-CZSL, UT-Zappos50K, Clothing16K) and group robustness on Waterbirds and CelebA. Code: https://github.com/nis-research/Compositionality-with-Primitives.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Embedding, Principle of compositionality, ENCODE, Robustness (evolution), Manifold (fluid mechanics), Mathematics

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange