arXiv AI July 14, 2026 By Hayeon Kim, Ji Ha Jang, Junghun James Kim, Se Young Chun

Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models

arXiv:2603. 22042v3 Announce Type: replace-cross Abstract: While Vision-Language Models (VLMs) have achieved remarkable performance, their Euclidean embeddings remain limited in capturing hierarchical relationships such as part-to-whole or parent-child structures, and often face challenges in multi-object compositional scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 1

Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training

arXiv:2608.29313v1 Announce Type: cross Abstract: CLIP-like vision-language models (VLMs) trained with contrastive objectives learn strong global image-text representations, but their Euclidean embed...

By Matin Mahmood, Antonio Rueda-Toicen, Mohamed ElBassat, Seifeldin Elkerdany, Weixing Wang, Gerard de Melo

llms rag multimodal safety

arXiv AI

Aug 11

Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings

arXiv:2603. 26798v2 Announce Type: replace-cross Abstract: Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected.

By Gesina Schwalbe, Mert Keser, Moritz Bayerkuhnlein, Edgar Heinert, Annika M\"utze, Marvin Keller, Sparsh Tiwari, Georgii Mikriukov, Diedrich Wolter, Jae Hee Lee, Matthias Rottmann

llms rag multimodal safety

arXiv AI

Jul 7

Text as Partial Constraint: Core-Residual Alignment for Robust Vision-Language Learning

arXiv:2607. 03143v1 Announce Type: cross Abstract: Vision-language alignment powers open-vocabulary recognition, retrieval, and LVLM grounding, yet natural captions are often underspecified, making similarity brittle and overly confident under paraphrase and omitted details.

By Chengzhen Yu, Canran Xiao, Siyuan Ma, Yang Liu

multimodal safety

arXiv AI

Jun 30

Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation

arXiv:2606. 29464v1 Announce Type: cross Abstract: Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently train contrastive vision-language models under strict data and compute budgets.

By Jongoh Jeong, Sun-Kyung Lee, Kuk-Jin Yoon

llms rag efficiency multimodal benchmarks safety

arXiv Computer Vision

Sep 15

HANCLIP: A Family of Hyperbolic Angular Negation Vision Language Models

arXiv:2606.23843v2 Announce Type: replace Abstract: Vision-language models (VLMs) achieve strong cross-modal alignment but remain brittle to negation, often relying on shallow word associations rathe...

By Hoang-Bao Le, Aiden Durrant, Thai Son Mai, Binh T. Nguyen, Liting Zhou, Cathal Gurrin

llms rag fine-tuning multimodal benchmarks safety

arXiv Computer Vision

Sep 22

Hierarchical Prompt Learning for Hyperbolic Vision-Language Models

arXiv:2609.24276v1 Announce Type: new Abstract: Hyperbolic vision-language models (VLMs) represent image and text features in a geometry naturally suited to hierarchy, but their adaptation to downstr...

By Andro Erdelez, Pascal Mettes, Behzad Bozorgtabar

llms rag multimodal benchmarks

One email a morning, machine-written

Related stories

Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training

Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings

Text as Partial Constraint: Core-Residual Alignment for Robust Vision-Language Learning

Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation

HANCLIP: A Family of Hyperbolic Angular Negation Vision Language Models

Hierarchical Prompt Learning for Hyperbolic Vision-Language Models