mlsanityData to 7 Oct 2026

ARGENT: Adaptive Hierarchical Image-Text Representations

arXiv 2603.23311 ↗First posted 24 Mar 2026cs.CV cs.LGcited by 1

On the map: Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP

Abstract (arXiv)

Large-scale Vision-Language Models (VLMs) such as CLIP learn powerful semantic representations but operate in Euclidean space, which fails to capture the inherent hierarchical structure of visual and linguistic concepts. Hyperbolic geometry, with its exponential volume growth, offers a principled alternative for embedding such hierarchies with low distortion. However, existing hyperbolic VLMs use entailment losses that are unstable: as parent embeddings contract toward the origin, their entailment cones widen toward a half-space, causing catastrophic cone collapse that destroys the intended hierarchy. Additionally, hierarchical evaluation of these models remains unreliable, being largely retrieval-based and correlation-based metrics and prone to taxonomy dependence and ambiguous negatives. To address these limitations, we propose an adaptive entailment loss paired with a norm regularizer that prevents cone collapse without heuristic aperture clipping. We further introduce an angle-based probabilistic entailment protocol (PEP) for evaluating hierarchical understanding, scored with AUC-ROC and Average Precision. This paper introduces a stronger hyperbolic VLM baseline ARGENT, Adaptive hieRarchical imaGe-tExt represeNTation. ARGENT improves the SOTA hyperbolic VLM by 0.7, 1.1, and 0.8 absolute points on image classification, text-to-image retrieval, and proposed hierarchical metrics, respectively.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 28 of its 37 references that are in the map. First posted on arXiv 24 Mar 2026.

Builds on

28 of 37 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Compositional Entailment Learning for Hyperbolic Vision-Language Models9 Oct
  2. 2024Hyperbolic Learning with Multimodal Large Language Models9 Aug

Other references · 26

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  4. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  5. 2025Qwen3-VL Technical Reportcited by 2,534
  6. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,352
  7. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  8. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  9. 2019Hyperbolic Graph Neural Networkscited by 244
  10. 2026Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Rankingcited by 211
  11. 2023Hyperbolic Image-Text Representationscited by 132
  12. 2018Embedding Text in Hyperbolic Spacescited by 76
14 more
  1. 2017Neural Embeddings of Graphs in Hyperbolic Spacecited by 58
  2. 2021HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projectionscited by 47
  3. 2023HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representationscited by 42
  4. 2024Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Spacecited by 39
  5. 2024Hyperbolic Fine-Tuning for Large Language Modelscited by 24
  6. 2024Emergent Visual-Semantic Hierarchies in Image-Text Representationscited by 19
  7. 2024HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Textscited by 17
  8. 2025HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learningcited by 17
  9. 2024Probabilistic Language-Image Pre-Trainingcited by 16
  10. 2023Contracting Skeletal Kinematics for Human-Related Video Anomaly Detectioncited by 13
  11. 2024HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image Retrievalcited by 11
  12. 2024A Fashion Item Recommendation Model in Hyperbolic Spacecited by 7
  13. 2024Embedding Geometries of Contrastive Language-Image Pre-Trainingcited by 6
  14. 2025Is Hyperbolic Space All You Need for Medical Anomaly Detection?cited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Is the Geometry Doing the Work? An Operating-Point Audit of Hierarchy in Hyperbolic Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Hierarchical Prompt Learning for Hyperbolic Vision-Language Models
  2. 2026Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models
  3. 2026Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training
  4. 2026HyperCLIP++: Fine-tuning CLIP forOpen-vocabulary Semantic Segmentation in Hyperbolic Space
  5. 2026Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings
  6. 2026Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation
  7. 2025Training-Free Dual Hyperbolic Adapters for Better Cross-Modal Reasoning
  8. 2025HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models