Imagen de Portada

Performance Plateaus in Inference-Time Scaling for Text-to-Image Diffusion Without External Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Choi, Changhyun, Kim, Sungha, Kim, H. Jin
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Memory-Efficient Personalization of Text-to-Image Diffusion Models via Selective Optimization Strategies
por: Choi, Seokeon, et al.
Publicado: (2025)

Text-Aware Image Restoration with Diffusion Models
por: Min, Jaewon, et al.
Publicado: (2025)

Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation
por: Kim, Taehoon, et al.
Publicado: (2025)

Steering Guidance for Personalized Text-to-Image Diffusion Models
por: Park, Sunghyun, et al.
Publicado: (2025)

Adversarial Robustification via Text-to-Image Diffusion Models
por: Choi, Daewon, et al.
Publicado: (2024)

Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
por: Kim, Jaihoon, et al.
Publicado: (2025)

Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning
por: Moon, Saemi, et al.
Publicado: (2024)

DiffBlender: Composable and Versatile Multimodal Text-to-Image Diffusion Models
por: Kim, Sungnyun, et al.
Publicado: (2023)

Feature Diversification and Adaptation for Federated Domain Generalization
por: Yang, Seunghan, et al.
Publicado: (2024)

Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales
por: Kim, Myeongsoo, et al.
Publicado: (2026)

Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models
por: Cho, Wonguk, et al.
Publicado: (2024)

MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual Editing
por: Kadambi, Shreya, et al.
Publicado: (2025)

Denoising Task Difficulty-based Curriculum for Training Diffusion Models
por: Kim, Jin-Young, et al.
Publicado: (2024)

Inference-Time Scaling of Diffusion Models for Infrared Data Generation
por: Horstmann, Kai A., et al.
Publicado: (2025)

Aligning Text to Image in Diffusion Models is Easier Than You Think
por: Lee, Jaa-Yeon, et al.
Publicado: (2025)

Efficient Scaling of Diffusion Transformers for Text-to-Image Generation
por: Li, Hao, et al.
Publicado: (2024)

Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps
por: Kim, Jeeyung, et al.
Publicado: (2024)

Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity
por: Lee, Hagyeong, et al.
Publicado: (2024)

EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation
por: Mun, Sunung, et al.
Publicado: (2026)

Parallel Tempering Initial Sampling in Inference-Time Reward Alignment
por: Oh, Myeongjun, et al.
Publicado: (2026)

Unified Control for Inference-Time Guidance of Denoising Diffusion Models
por: Goyal, Maurya, et al.
Publicado: (2025)

Generalized Contrastive Learning for Universal Multimodal Retrieval
por: Lee, Jungsoo, et al.
Publicado: (2025)

Improving Diffusion-Based Generative Models via Approximated Optimal Transport
por: Kim, Daegyu, et al.
Publicado: (2024)

EdgeFusion: On-Device Text-to-Image Generation
por: Castells, Thibault, et al.
Publicado: (2024)

Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation
por: Ye, Jinyan, et al.
Publicado: (2026)

Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance
por: Lin, Kuan Heng, et al.
Publicado: (2024)

Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model
por: Yi, Mingyang, et al.
Publicado: (2024)

Toward Early Quality Assessment of Text-to-Image Diffusion Models
por: Guo, Huanlei, et al.
Publicado: (2026)

Improving Long-Text Alignment for Text-to-Image Diffusion Models
por: Liu, Luping, et al.
Publicado: (2024)

ViPCap: Retrieval Text-Based Visual Prompts for Lightweight Image Captioning
por: Kim, Taewhan, et al.
Publicado: (2024)

Frequency-Calibrated Membership Inference Attacks on Medical Image Diffusion Models
por: Zhao, Xinkai, et al.
Publicado: (2025)

SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models
por: Lu, Mingyu, et al.
Publicado: (2026)

Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
por: Ling, Huan, et al.
Publicado: (2023)

Directional Textual Inversion for Personalized Text-to-Image Generation
por: Kim, Kunhee, et al.
Publicado: (2025)

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models
por: Choi, Hyesong, et al.
Publicado: (2024)

DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models
por: Ryu, Hyogon, et al.
Publicado: (2025)

CustomText: Customized Textual Image Generation using Diffusion Models
por: Paliwal, Shubham, et al.
Publicado: (2024)

Prompt-Based Safety Guidance Is Ineffective for Unlearned Text-to-Image Diffusion Models
por: Shin, Jiwoo, et al.
Publicado: (2025)

Progressive Compositionality in Text-to-Image Generative Models
por: Han, Evans Xu, et al.
Publicado: (2024)

Tutorial on Diffusion Models for Imaging and Vision
por: Chan, Stanley H.
Publicado: (2024)