Imagen de Portada

Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sun, Haoyuan, Xia, Bo, Chang, Yongzhe, Wang, Xueqian
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation
por: Luo, Yifu, et al.
Publicado: (2025)

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models
por: Sun, Haoyuan, et al.
Publicado: (2025)

Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping
por: Sun, Haoyuan, et al.
Publicado: (2026)

MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment
por: Gao, Zhiting, et al.
Publicado: (2025)

Learning Multi-dimensional Human Preference for Text-to-Image Generation
por: Zhang, Sixian, et al.
Publicado: (2024)

Fast Prompt Alignment for Text-to-Image Generation
por: Mrini, Khalil, et al.
Publicado: (2024)

Scalable Ranked Preference Optimization for Text-to-Image Generation
por: Karthik, Shyamgopal, et al.
Publicado: (2024)

AGFSync: Leveraging AI-Generated Feedback for Preference Optimization in Text-to-Image Generation
por: An, Jingkun, et al.
Publicado: (2024)

Unleashing the Potential of Large Language Models for Text-to-Image Generation through Autoregressive Representation Alignment
por: Xie, Xing, et al.
Publicado: (2025)

Instant Preference Alignment for Text-to-Image Diffusion Models
por: Li, Yang, et al.
Publicado: (2025)

HCMA: Hierarchical Cross-model Alignment for Grounded Text-to-Image Generation
por: Wang, Hang, et al.
Publicado: (2025)

Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization
por: Luo, Yifu, et al.
Publicado: (2025)

Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation
por: Wang, Zihao, et al.
Publicado: (2026)

BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment
por: Zhou, Dewei, et al.
Publicado: (2025)

FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL
por: Pan, Kaihang, et al.
Publicado: (2025)

DETONATE: A Benchmark for Text-to-Image Alignment and Kernelized Direct Preference Optimization
por: Prasad, Renjith, et al.
Publicado: (2025)

Instruction-augmented Multimodal Alignment for Image-Text and Element Matching
por: Yue, Xinli, et al.
Publicado: (2025)

OSPO: Object-Centric Self-Improving Preference Optimization for Text-to-Image Generation
por: Oh, Yoonjin, et al.
Publicado: (2025)

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

TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm
por: Zhang, Bingqing, et al.
Publicado: (2024)

High Fidelity Text to Image Generation with Contrastive Alignment and Structural Guidance
por: Gao, Danyi
Publicado: (2025)

What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment
por: Parthasarathy, Rishab, et al.
Publicado: (2025)

Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think
por: Chen, Liang, et al.
Publicado: (2025)

UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception
por: Song, Xinyang, et al.
Publicado: (2025)

Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment
por: Ba, Ying, et al.
Publicado: (2025)

TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards
por: Cui, Mingxuan, et al.
Publicado: (2026)

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

Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
por: Liu, Zhuohan, et al.
Publicado: (2026)

Exploring Motion-Language Alignment for Text-driven Motion Generation
por: Gu, Ruxi, et al.
Publicado: (2026)

CritiFusion: Semantic Critique and Spectral Alignment for Faithful Text-to-Image Generation
por: Chen, ZhenQi, et al.
Publicado: (2025)

Hierarchical Vision-Language Alignment for Text-to-Image Generation via Diffusion Models
por: Johnson, Emily, et al.
Publicado: (2025)

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

Preference Alignment on Diffusion Model: A Comprehensive Survey for Image Generation and Editing
por: Wu, Sihao, et al.
Publicado: (2025)

HuViDPO:Enhancing Video Generation through Direct Preference Optimization for Human-Centric Alignment
por: Jiang, Lifan, et al.
Publicado: (2025)

LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization
por: Wu, Xianfeng, et al.
Publicado: (2025)

Cross Paradigm Representation and Alignment Transformer for Image Deraining
por: Zou, Shun, et al.
Publicado: (2025)

Generalized Small Object Detection:A Point-Prompted Paradigm and Benchmark
por: Zhu, Haoran, et al.
Publicado: (2026)

Anomaly-Preference Image Generation
por: Wang, Fuyun, et al.
Publicado: (2026)

CSGO: Content-Style Composition in Text-to-Image Generation
por: Xing, Peng, et al.
Publicado: (2024)

Text2Traffic: A Text-to-Image Generation and Editing Method for Traffic Scenes
por: Lv, Feng, et al.
Publicado: (2025)