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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

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 AI

Jul 7

Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models

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.

By Hulingxiao He, Zhi Tan, Yuxin Peng

llms rag fine-tuning multimodal

arXiv Machine Learning

Aug 4

GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding

arXiv:2605. 13352v2 Announce Type: replace Abstract: Standard dual-encoder vision-language models that map images and text to deterministic points on a shared unit hypersphere through $\ell_2$ normalization typically expose neither \emph{aleatoric} uncertainty (cross-modal ambiguity) nor \emph{epistemic} uncertainty (lack of training-distribution support).

By Mayank Nautiyal, Li Ju, Andreas Hellander, Ekta Vats, Prashant Singh

llms rag diffusion multimodal benchmarks

arXiv AI

Jun 12

GeoWorld-VLM: Geometry from World Models for Vision-Language Models

arXiv:2605. 16713v2 Announce Type: replace-cross Abstract: Modern Vision-Language Models (VLMs) achieve strong semantic recognition, yet remain brittle on elementary spatial relations such as left of, on, behind, and between.

By Renjie Gu, Kaichen Zhou, Yan Luo, Mengyu Wang

llms efficiency multimodal benchmarks safety

Related stories

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

Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models

GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding

GeoWorld-VLM: Geometry from World Models for Vision-Language Models