HypCBM reformulates concept activations as geometric containment in hyperbolic space to produce sparse, hierarchy-aware signals that match Euclidean models trained on 20 times more data.
Compositional entailment learning for hyperbolic vision-language models.arXiv preprint arXiv:2410.06912
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
dataset 1polarities
use dataset 1representative citing papers
Level-restricted contrastive learning with group balancing improves hierarchical consistency and accuracy in zero-shot fine-grained vision classification.
Hyperbolic Scene Graph (HSG) learns embeddings in hyperbolic space for better hierarchical structure in scene graphs, achieving graph IoU of 33.51 versus 25.37 for the best Euclidean baseline.
GeoWorld applies hyperbolic geometry to JEPA world models and introduces geometric reinforcement learning, reporting modest success-rate gains of ~3% and ~2% on 3- and 4-step planning tasks versus V-JEPA 2.
HyperVLP uses hyperbolic geometry in surgical video-language pre-training to preserve hierarchy across actions, steps, and phases, yielding gains in zero- and few-shot phase recognition.
citing papers explorer
-
Hyperbolic Concept Bottleneck Models
HypCBM reformulates concept activations as geometric containment in hyperbolic space to produce sparse, hierarchy-aware signals that match Euclidean models trained on 20 times more data.
-
Beyond Flat Labels: Level-Restricted Contrastive Learning for Hierarchical Fine-Grained Vision Classification
Level-restricted contrastive learning with group balancing improves hierarchical consistency and accuracy in zero-shot fine-grained vision classification.
-
HSG: Hyperbolic Scene Graph
Hyperbolic Scene Graph (HSG) learns embeddings in hyperbolic space for better hierarchical structure in scene graphs, achieving graph IoU of 33.51 versus 25.37 for the best Euclidean baseline.
-
GeoWorld: Geometric World Models
GeoWorld applies hyperbolic geometry to JEPA world models and introduces geometric reinforcement learning, reporting modest success-rate gains of ~3% and ~2% on 3- and 4-step planning tasks versus V-JEPA 2.
-
HyperVLP: Enhancing Hierarchical Surgical Video-Language Pre-training in Hyperbolic Space
HyperVLP uses hyperbolic geometry in surgical video-language pre-training to preserve hierarchy across actions, steps, and phases, yielding gains in zero- and few-shot phase recognition.