Cover Image

SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Grimal, Paul, Soumm, Michaël, Borgne, Hervé Le, Ferret, Olivier, Sugimoto, Akihiro
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Text-to-Image Alignment in Denoising-Based Models through Step Selection
by: Grimal, Paul, et al.
Published: (2025)

TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation
by: Grimal, Paul, et al.
Published: (2023)

Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification
by: Fournier-Montgieux, Alexandre, et al.
Published: (2024)

Toward Fairer Face Recognition Datasets
by: Fournier-Montgieux, Alexandre, et al.
Published: (2024)

Learning Common and Salient Generative Factors Between Two Image Datasets
by: He, Yunlong, et al.
Published: (2025)

SAGA: Surface-Aligned Gaussian Avatar
by: Chen, Ronghan, et al.
Published: (2024)

Measuring Image-Relation Alignment: Reference-Free Evaluation of VLMs and Synthetic Pre-training for Open-Vocabulary Scene Graph Generation
by: Neau, Maëlic, et al.
Published: (2025)

Automatic Die Studies for Ancient Numismatics
by: Cornet, Clément, et al.
Published: (2024)

Explaining How Visual, Textual and Multimodal Encoders Share Concepts
by: Cornet, Clément, et al.
Published: (2025)

Smooth Pseudo-Labeling
by: Karaliolios, Nikolaos, et al.
Published: (2024)

TESO: Online Tracking of Essential Matrix by Stochastic Optimization
by: Moravec, Jaroslav, et al.
Published: (2026)

EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension
by: Li, Jiaxuan, et al.
Published: (2023)

Reliable and Reproducible Demographic Inference for Fairness in Face Analysis
by: Fournier-Montgieux, Alexandre, et al.
Published: (2025)

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

Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation
by: Hu, Zijing, et al.
Published: (2025)

Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation
by: Eldesokey, Abdelrahman, et al.
Published: (2026)

Fair Text to Medical Image Diffusion Model with Subgroup Distribution Aligned Tuning
by: Han, Xu, et al.
Published: (2024)

Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text
by: Liang, Guotao, et al.
Published: (2025)

Aligned Datasets Improve Detection of Latent Diffusion-Generated Images
by: Rajan, Anirudh Sundara, et al.
Published: (2024)

PopAlign: Population-Level Alignment for Fair Text-to-Image Generation
by: Li, Shufan, et al.
Published: (2024)

TIQA: Human-Aligned Perceptual Text Quality Assessment in Generated Images
by: Koltsov, Kirill, et al.
Published: (2026)

SAGA: Source Attribution of Generative AI Videos
by: Kundu, Rohit, et al.
Published: (2025)

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment
by: Li, Yuheng, et al.
Published: (2024)

Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation
by: Zhang, Wenchao, et al.
Published: (2025)

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

REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation
by: Neau, Maëlic, et al.
Published: (2024)

MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection
by: Lahlali, Saad, et al.
Published: (2025)

ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only
by: Lahlali, Saad, et al.
Published: (2024)

TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models
by: Xiao, Yao, et al.
Published: (2025)

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
by: Fu, Minghao, et al.
Published: (2025)

T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability
by: Khosla, Savya, et al.
Published: (2026)

AlignedGen: Aligning Style Across Generated Images
by: Zhang, Jiexuan, et al.
Published: (2025)

CaMiT: A Time-Aware Car Model Dataset for Classification and Generation
by: LIN, Frédéric, et al.
Published: (2025)

Continual Learning for Image Captioning through Improved Image-Text Alignment
by: Taetz, Bertram, et al.
Published: (2025)

CompAlign: Improving Compositional Text-to-Image Generation with a Complex Benchmark and Fine-Grained Feedback
by: Wan, Yixin, et al.
Published: (2025)

Aligning Text, Images, and 3D Structure Token-by-Token
by: Sahoo, Aadarsh, et al.
Published: (2025)

AlignIT: Enhancing Prompt Alignment in Customization of Text-to-Image Models
by: Agarwal, Aishwarya, et al.
Published: (2024)

Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models
by: Miyake, Daiki, et al.
Published: (2023)

SAGA: Selective Adaptive Gating for Efficient and Expressive Linear Attention
by: Cao, Yuan, et al.
Published: (2025)

AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation
by: Liu, Yexin, et al.
Published: (2025)