Image de couverture de livre

Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xie, Dian, Shao, Shitong, Bai, Lichen, Zhou, Zikai, Cheng, Bojun, Yang, Shuo, Wu, Jun, Xie, Zeke
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Optimizing Few-Step Generation with Adaptive Matching Distillation
par: Bai, Lichen, et autres
Publié: (2026)

CoRe^2: Collect, Reflect and Refine to Generate Better and Faster
par: Shao, Shitong, et autres
Publié: (2025)

IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis
par: Shao, Shitong, et autres
Publié: (2024)

Exploring Data-Free LoRA Transferability for Video Diffusion Models
par: Wang, Yuchen, et autres
Publié: (2026)

Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer
par: Shao, Shitong, et autres
Publié: (2024)

CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think
par: Sun, Zening, et autres
Publié: (2026)

LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
par: Shao, Shitong, et autres
Publié: (2026)

PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers
par: Li, Haopeng, et autres
Publié: (2026)

Golden Noise for Diffusion Models: A Learning Framework
par: Zhou, Zikai, et autres
Publié: (2024)

Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection
par: Bai, Lichen, et autres
Publié: (2024)

Reflective Flow Sampling Enhancement
par: Zhou, Zikai, et autres
Publié: (2026)

Efficient Video Diffusion Models: Advancements and Challenges
par: Shao, Shitong, et autres
Publié: (2026)

FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters
par: Shao, Shitong, et autres
Publié: (2026)

Weak-to-Strong Diffusion with Reflection
par: Bai, Lichen, et autres
Publié: (2025)

Not All Noises Are Created Equally:Diffusion Noise Selection and Optimization
par: Qi, Zipeng, et autres
Publié: (2024)

Rethinking Centered Kernel Alignment in Knowledge Distillation
par: Zhou, Zikai, et autres
Publié: (2024)

Alignment of Diffusion Models: Fundamentals, Challenges, and Future
par: Liu, Buhua, et autres
Publié: (2024)

Elucidating the Design Space of Dataset Condensation
par: Shao, Shitong, et autres
Publié: (2024)

MagicDistillation: Weak-to-Strong Video Distillation for Large-Scale Few-Step Synthesis
par: Shao, Shitong, et autres
Publié: (2025)

Accelerating Diffusion Model Training under Minimal Budgets: A Condensation-Based Perspective
par: Huang, Rui, et autres
Publié: (2025)

Fused attention mechanism-based ore sorting network
par: Zhen, Junjiang, et autres
Publié: (2024)

DreamView: Injecting View-specific Text Guidance into Text-to-3D Generation
par: Yan, Junkai, et autres
Publié: (2024)

Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training
par: Sun, Peng, et autres
Publié: (2026)

CDPDNet: Integrating Text Guidance with Hybrid Vision Encoders for Medical Image Segmentation
par: Wu, Jiong, et autres
Publié: (2025)

MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice
par: Yi, Hongwei, et autres
Publié: (2025)

Conditional Text-to-Image Generation with Reference Guidance
par: Kim, Taewook, et autres
Publié: (2024)

3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation
par: Zhou, Dewei, et autres
Publié: (2024)

Robust Remote Sensing Image-Text Retrieval with Noisy Correspondence
par: Song, Qiya, et autres
Publié: (2026)

Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression
par: Meng, Zichong, et autres
Publié: (2024)

Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation
par: Cheng, Jiaxin, et autres
Publié: (2024)

Beyond Flat Text: Dual Self-inherited Guidance for Visual Text Generation
par: Luo, Minxing, et autres
Publié: (2025)

Text-Image Conditioned 3D Generation
par: Cen, Jiazhong, et autres
Publié: (2026)

KB-DMGen: Knowledge-Based Global Guidance and Dynamic Pose Masking for Human Image Generation
par: Liu, Shibang, et autres
Publié: (2025)

MangaFlow: An End-to-End Agentic Framework for Controllable Story to Manga Generation
par: Wang, Muyao, et autres
Publié: (2026)

Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation
par: Li, Niantong, et autres
Publié: (2026)

Rethinking Concept Bottleneck Models: From Pitfalls to Solutions
par: Tapli, Merve, et autres
Publié: (2026)

PIG: Prompt Images Guidance for Night-Time Scene Parsing
par: Xie, Zhifeng, et autres
Publié: (2024)

Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation
par: Li, Yaqi, et autres
Publié: (2025)

Tuning-Free Image Customization with Image and Text Guidance
par: Li, Pengzhi, et autres
Publié: (2024)

Power Line Aerial Image Restoration under dverse Weather: Datasets and Baselines
par: Yang, Sai, et autres
Publié: (2024)