Imagen de Portada

What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Parthasarathy, Rishab, Collins, Jasmine, Stephenson, Cory
Formato:	Preprint
Publicado:	2025
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

What Makes for Good Image Captions?
por: Chen, Delong, et al.
Publicado: (2024)

What Makes for a Good Stereoscopic Image?
por: Tamir, Netanel Y., et al.
Publicado: (2024)

Vid3D: Synthesis of Dynamic 3D Scenes using 2D Video Diffusion
por: Parthasarathy, Rishab, et al.
Publicado: (2024)

Image Understanding Makes for A Good Tokenizer for Image Generation
por: Wang, Luting, et al.
Publicado: (2024)

Implicit Preference Alignment for Human Image Animation
por: Wang, Yuanzhi, et al.
Publicado: (2026)

Aligning Multimodal LLM with Human Preference: A Survey
por: Yu, Tao, et al.
Publicado: (2025)

What Makes a Good Dataset for Knowledge Distillation?
por: Frank, Logan, et al.
Publicado: (2024)

Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization
por: Sun, Haoyuan, et al.
Publicado: (2024)

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

Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models
por: Xu, Katherine, et al.
Publicado: (2024)

PrefGen: Multimodal Preference Learning for Preference-Conditioned Image Generation
por: Mo, Wenyi, et al.
Publicado: (2025)

Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable
por: Chen, Ruoxin, et al.
Publicado: (2025)

Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment
por: Le, Minh-Quan, et al.
Publicado: (2025)

Are Multimodal Large Language Models Good Annotators for Image Tagging?
por: Xie, Ming-Kun, et al.
Publicado: (2026)

Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences
por: Bahng, Hyojin, et al.
Publicado: (2025)

MedM-VL: What Makes a Good Medical LVLM?
por: Shi, Yiming, et al.
Publicado: (2025)

How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?
por: Chen, Yuxin, et al.
Publicado: (2024)

Towards Anatomically Plausible Human Image Generation via Synthetic Localized Preferences
por: Li, Bao, et al.
Publicado: (2026)

What Makes Synthetic Data Effective in Image Segmentation
por: Zhang, Jinjin, et al.
Publicado: (2026)

Good Noise Makes Good Edits: A Training-Free Diffusion-Based Video Editing with Image and Text Prompts
por: Choi, Saemee, et al.
Publicado: (2025)

Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor
por: Lin, Ethan, et al.
Publicado: (2025)

What Makes Good Few-shot Examples for Vision-Language Models?
por: Guo, Zhaojun, et al.
Publicado: (2024)

ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation?
por: Zhang, Leixin, et al.
Publicado: (2024)

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

GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing
por: Wang, Zhenyu, et al.
Publicado: (2024)

MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation
por: Song, Kunpeng, et al.
Publicado: (2024)

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

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

Learning User Preferences for Image Generation Model
por: Mo, Wenyi, et al.
Publicado: (2025)

Image Score: Learning and Evaluating Human Preferences for Mercari Search
por: Oinar, Chingis, et al.
Publicado: (2024)

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

VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
por: Xu, Jiazheng, et al.
Publicado: (2024)

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

What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?
por: Yan, David, et al.
Publicado: (2025)

VideoRoPE: What Makes for Good Video Rotary Position Embedding?
por: Wei, Xilin, et al.
Publicado: (2025)

Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment
por: Park, Sangha, et al.
Publicado: (2025)

Rich Human Feedback for Text-to-Image Generation
por: Liang, Youwei, et al.
Publicado: (2023)

Canvas-to-Image: Compositional Image Generation with Multimodal Controls
por: Dalva, Yusuf, et al.
Publicado: (2025)

Face-MakeUp: Multimodal Facial Prompts for Text-to-Image Generation
por: Dai, Dawei, et al.
Publicado: (2025)

PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
por: Liu, Kendong, et al.
Publicado: (2024)