Imagen de Portada

Geometrical Properties of Text Token Embeddings for Strong Semantic Binding in Text-to-Image Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Seo, Hoigi, Bang, Junseo, Lee, Haechang, Lee, Joohoon, Lee, Byung Hyun, Chun, Se Young
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models
por: Seo, Hoigi, et al.
Publicado: (2026)

Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution
por: Bang, Junseo, et al.
Publicado: (2025)

On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
por: Seo, Hoigi, et al.
Publicado: (2025)

Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation
por: Seo, Hoigi, et al.
Publicado: (2025)

Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity Schedules
por: Bang, Junseo, et al.
Publicado: (2026)

Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation
por: Lee, Byung Hyun, et al.
Publicado: (2025)

Efficient Personalization of Quantized Diffusion Model without Backpropagation
por: Seo, Hoigi, et al.
Publicado: (2025)

Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformers
por: Jeong, Wongi, et al.
Publicado: (2025)

Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models
por: Jeong, Wongi, et al.
Publicado: (2026)

Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate
por: Lee, Byung Hyun, et al.
Publicado: (2025)

INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding
por: Jang, Ji Ha, et al.
Publicado: (2024)

Continual Multiple Instance Learning with Enhanced Localization for Histopathological Whole Slide Image Analysis
por: Lee, Byung Hyun, et al.
Publicado: (2025)

Unlearning the Unpromptable: Prompt-free Instance Unlearning in Diffusion Models
por: Lee, Kyungryeol, et al.
Publicado: (2026)

Doubly Perturbed Task Free Continual Learning
por: Lee, Byung Hyun, et al.
Publicado: (2023)

Iterative Prompt Refinement for Safer Text-to-Image Generation
por: Jeon, Jinwoo, et al.
Publicado: (2025)

Semantic Guidance Tuning for Text-To-Image Diffusion Models
por: Kang, Hyun, et al.
Publicado: (2023)

BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion
por: Kim, Gwanghyun, et al.
Publicado: (2024)

ID-EA: Identity-driven Text Enhancement and Adaptation with Textual Inversion for Personalized Text-to-Image Generation
por: Jin, Hyun-Jun, et al.
Publicado: (2025)

DECOR:Decomposition and Projection of Text Embeddings for Text-to-Image Customization
por: Jang, Geonhui, et al.
Publicado: (2024)

Local Representative Token Guided Merging for Text-to-Image Generation
por: Lee, Min-Jeong, et al.
Publicado: (2025)

StyleForge: Enhancing Text-to-Image Synthesis for Any Artistic Styles with Dual Binding
por: Park, Junseo, et al.
Publicado: (2024)

Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
por: Hu, Taihang, et al.
Publicado: (2024)

Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings
por: Zarei, Arman, et al.
Publicado: (2024)

LaMoGen: Laban Movement-Guided Diffusion for Text-to-Motion Generation
por: Kim, Heechang, et al.
Publicado: (2025)

Personalized Reward Modeling for Text-to-Image Generation
por: Lee, Jeongeun, et al.
Publicado: (2025)

Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models
por: Koh, Eunseo, et al.
Publicado: (2025)

MATE: Meet At The Embedding -- Connecting Images with Long Texts
por: Jang, Young Kyun, et al.
Publicado: (2024)

Improving Text Generation on Images with Synthetic Captions
por: Koh, Jun Young, et al.
Publicado: (2024)

Geometric Disentanglement of Text Embeddings for Subject-Consistent Text-to-Image Generation using A Single Prompt
por: Li, Shangxun, et al.
Publicado: (2025)

CountCluster: Training-Free Object Quantity Guidance with Cross-Attention Map Clustering for Text-to-Image Generation
por: Lee, Joohyeon, et al.
Publicado: (2025)

Text Embedding Knows How to Quantize Text-Guided Diffusion Models
por: Lee, Hongjae, et al.
Publicado: (2025)

Structured State-Space Regularization for Generation-Friendly Image Tokenization
por: Lee, Jinsung, et al.
Publicado: (2026)

FlipConcept: Tuning-Free Multi-Concept Personalization for Text-to-Image Generation
por: Woo, Young Beom, et al.
Publicado: (2025)

Evaluating the Generation of Spatial Relations in Text and Image Generative Models
por: Sim, Shang Hong, et al.
Publicado: (2024)

Efficient and robust 3D blind harmonization for large domain gaps
por: Jeong, Hwihun, et al.
Publicado: (2025)

Bridging Geometric and Semantic Foundation Models for Generalized Monocular Depth Estimation
por: Ma, Sanggyun, et al.
Publicado: (2025)

Object-Attribute Binding in Text-to-Image Generation: Evaluation and Control
por: Trusca, Maria Mihaela, et al.
Publicado: (2024)

Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation
por: Choi, Jiho, et al.
Publicado: (2025)

AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
por: Pang, Lianyu, et al.
Publicado: (2024)

Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation
por: Wu, Ji-Jia, et al.
Publicado: (2024)