mlsanityData to 7 Oct 2026

Hierarchical Prompt Learning for Hyperbolic Vision-Language Models

arXiv 2609.24276 ↗First posted 21 Sep 2026cs.CVcited by 0

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

Abstract (arXiv)

Hyperbolic vision-language models (VLMs) represent image and text features in a geometry naturally suited to hierarchy, but their adaptation to downstream tasks has largely relied on fixed prompts. Existing prompt learning methods, meanwhile, treat class labels as a flat set and do not exploit available taxonomic structure. We address this gap with a hierarchical prompt learning plug-in for frozen hyperbolic VLMs. Given a fixed offline parent-class hierarchy, it augments a class prompt learner with a separate parent prompt learner, parent-level supervision, hyperbolic entailment regularization, and parent-feedback logit fusion. We instantiate the method with CoOp, CoCoOp and MaPLe, yielding HyPLO, CoHyPLO and MaHyPLO. Across the standard 11-dataset benchmark, all variants improve base-to-new generalization and cross-dataset transfer, and remain comparable to their prompt learning baselines under domain shift. Six hierarchical metrics and embedding analyses show that the method produces more taxonomically consistent predictions and induces a hierarchy-consistent organization of parent, class, and image embeddings in hyperbolic space. Its gains are largest when novel classes must be placed within a fixed taxonomy, and smallest for fine-grained confusions among sibling classes or shifts affecting only the image distribution.

Key facts. No citing papers in the map yet (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 32 of its 49 references that are in the map. First posted on arXiv 21 Sep 2026.

Builds on

32 of 49 references.

Closest ancestors · 10

Same direction, newest first

  1. 2026Semantic Alignment in Hyperbolic Space for Open-Vocabulary Semantic Segmentation9 May
  2. 2025Hyperbolic Deep Learning for Foundation Models: A Survey23 Jul
  3. 2025Hierarchical Cross-modal Prompt Learning for Vision-Language Models20 Jul
  4. 2024IPO: Interpretable Prompt Optimization for Vision-Language Models20 Oct
  5. 2024Compositional Entailment Learning for Hyperbolic Vision-Language Models9 Oct
  6. 2024Hyperbolic Learning with Multimodal Large Language Models9 Aug
  7. 2023HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding23 Nov
  8. 2023Consistency-guided Prompt Learning for Vision-Language Models1 Jun
  9. 2022Conditional Prompt Learning for Vision-Language Models10 Mar
  10. 2021Learning to Prompt for Vision-Language Models2 Sep

Other references · 22

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2013Describing Textures in the Wildcited by 2,110
  3. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  4. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
  5. 2022MaPLe: Multi-modal Prompt Learningcited by 685
  6. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  7. 2018Hyperbolic Neural Networkscited by 393
  8. 2023Self-regulating Prompts: Foundational Model Adaptation without Forgettingcited by 272
  9. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 261
  10. 2018Representation Tradeoffs for Hyperbolic Embeddingscited by 204
  11. 2018Hyperbolic Entailment Cones for Learning Hierarchical Embeddingscited by 160
  12. 2023Hyperbolic Image-Text Representationscited by 132
10 more
  1. 2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 109
  2. 2022Hyperbolic Image Segmentationcited by 101
  3. 2023Hyperbolic Deep Learning in Computer Vision: A Surveycited by 72
  4. 2013Evaluation Measures for Hierarchical Classification: a unified view and novel approachescited by 46
  5. 2020Hierarchical Image Classification using Entailment Cone Embeddingscited by 46
  6. 2021Hyperbolic Busemann Learning with Ideal Prototypescited by 40
  7. 2025Hyperbolic Safety-Aware Vision-Language Modelscited by 17
  8. 2025HyperCore: The Core Framework for Building Hyperbolic Foundation Models with Comprehensive Modulescited by 12
  9. 2024Learning Visual Hierarchies in Hyperbolic Space for Image Retrievalcited by 8
  10. 2025PHyCLIP: ℓ1-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learningcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Is the Geometry Doing the Work? An Operating-Point Audit of Hierarchy in Hyperbolic Vision-Language Models
  2. 2026ARGENT: Adaptive Hierarchical Image-Text Representations
  3. 2026Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training
  4. 2026Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models
  5. 2025Training-Free Dual Hyperbolic Adapters for Better Cross-Modal Reasoning
  6. 2026Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation
  7. 2026HMVLA: Hyperbolic Multimodal Fusion for Vision-Language-Action Models
  8. 2025Hierarchy-Aware Fine-Tuning of Vision-Language Models