Is the Geometry Doing the Work? An Operating-Point Audit of Hierarchy in Hyperbolic Vision-Language Models
cs.CV, cs.LG
Submitted: 2026-07-06
Updated: 2026-11-12
Terminology
Sources
- HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention
- ARGENT: Adaptive Hierarchical Image-Text Representations
- Order-Embeddings of Images and Language
- PHyCLIP: $\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning
- VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs