Not All Latent Spaces Are Flat: Hyperbolic Concept Control
As modern text-to-image (T2I) models draw closer to synthesizing highly realistic content, the threat of unsafe content generation grows, and it becomes paramount to exercise control. Existing approaches steer these models by applying Euclidean adjustments to text embeddings, redirecting the generation away from unsafe concepts. In this work, we introduce hyperbolic control (HyCon): a novel control mechanism based on parallel transport that leverages semantically aligned hyperbolic representation space to yield more expressive and stable manipulation of concepts. HyCon reuses off-the-shelf generative models and a state-of-the-art hyperbolic text encoder, linked via a lightweight adapter. HyCon achieves state-of-the-art results across four safety benchmarks and four T2I backbones, showing that hyperbolic steering is a practical and flexible approach for more reliable T2I generation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Hyperbolic Diffusion Recommender Model
Diffusion models (DMs) have emerged as the new state-of-the-art family of deep generative models. To gain deeper insights into the limitations of diffusion models in recommender systems, we investigate the fundamental st…
modelRecommendation SystemsHybed: Hyperbolic Neural Graph Embedding
Neural embeddings have been used with great success in Natural Language Processing (NLP) where they provide compact representations that encapsulate word similarity and attain state-of-the-art performance in a range of l…
Graph EmbeddingWord SimilaritySome steps towards the generation of diachronic WordNets
We apply hyperbolic embeddings to trace the dynamics of change of conceptual-semantic relationships in a large diachronic scientific corpus (200 years). Our focus is on emerging scientific fields and the increasingly spe…
Neural Embeddings of Graphs in Hyperbolic Space
Neural embeddings have been used with great success in Natural Language Processing (NLP). They provide compact representations that encapsulate word similarity and attain state-of-the-art performance in a range of lingui…
Word SimilarityLatent Variable Modelling with Hyperbolic Normalizing Flows
The choice of approximate posterior distributions plays a central role in stochastic variational inference (SVI). One effective solution is the use of normalizing flows \cut{defined on Euclidean spaces} to construct flex…
Density EstimationVariational Inference