Imagen de Portada

Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wu, Ge, Zhang, Shen, Shi, Ruijing, Gao, Shanghua, Chen, Zhenyuan, Wang, Lei, Chen, Zhaowei, Gao, Hongcheng, Tang, Yao, Yang, Jian, Cheng, Ming-Ming, Li, Xiang
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

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
por: Yu, Sihyun, et al.
Publicado: (2024)

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

CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think
por: Sun, Zening, et al.
Publicado: (2026)

Identification in (Endogenously) Nonlinear SVARs Is Easier Than You Think
por: Duffy, James A., et al.
Publicado: (2026)

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

MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer
por: Gao, Shanghua, et al.
Publicado: (2023)

Representation Alignment for Just Image Transformers is not Easier than You Think
por: Shin, Jaeyo, et al.
Publicado: (2026)

Fine-tuning MLLMs Without Forgetting Is Easier Than You Think
por: Li, He, et al.
Publicado: (2026)

Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think
por: Tian, Jie, et al.
Publicado: (2025)

Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
por: Garcia, Gonzalo Martin, et al.
Publicado: (2024)

Conditioning Matters: Training Diffusion Policies is Faster Than You Think
por: Dong, Zibin, et al.
Publicado: (2025)

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
por: Feng, Tao, et al.
Publicado: (2025)

Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
por: Li, Ouxiang, et al.
Publicado: (2025)

Let Me Count the Ways: Teaching Math in the Library May Seem Like a Stretch. But It's Easier Than You Think
por: Fleming, Dan
Publicado: (2004)

CoDAR: Continuous Diffusion Language Models are More Powerful Than You Think
por: Shen, Junzhe, et al.
Publicado: (2026)

V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think
por: Tang, Bingda, et al.
Publicado: (2026)

Can We Change the Stroke Size for Easier Diffusion?
por: Bai, Yunwei, et al.
Publicado: (2026)

HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models
por: Zhang, Shen, et al.
Publicado: (2023)

You Can Backdoor Personalized Federated Learning
por: Ye, Tiandi, et al.
Publicado: (2023)

To Copy or Not to Copy: Copying Is Easier to Induce Than Recall
por: Farahani, Mehrdad, et al.
Publicado: (2026)

Asymptotic Fair Division: Chores Are Easier Than Goods
por: Manurangsi, Pasin, et al.
Publicado: (2025)

ResNets Are Deeper Than You Think
por: Mehmeti-Göpel, Christian H. X. Ali, et al.
Publicado: (2025)

The Weak Form Is Stronger Than You Think
por: Messenger, Daniel A., et al.
Publicado: (2024)

LoRA Is Slower Than You Think
por: Ko, Seokmin
Publicado: (2025)

Jailbreaking is (Mostly) Simpler Than You Think
por: Russinovich, Mark, et al.
Publicado: (2025)

Thinking with Patterns: Breaking the Perceptual Bottleneck in Visual Planning via Pattern Induction
por: Jian, Yichang, et al.
Publicado: (2026)

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding
por: Zhang, Shen, et al.
Publicado: (2025)

Revisiting Prompt Pretraining of Vision-Language Models
por: Chen, Zhenyuan, et al.
Publicado: (2024)

Min-Max Optimization Is Strictly Easier Than Variational Inequalities
por: Shugart, Henry, et al.
Publicado: (2025)

Your Embedding Model is SMARTer Than You Think
por: Zhang, Jianrui, et al.
Publicado: (2026)

Intermediate Outputs Are More Sensitive Than You Think
por: Huang, Tao, et al.
Publicado: (2024)

Geometric Meta-Learning via Coupled Ricci Flow: Unifying Knowledge Representation and Quantum Entanglement
por: Lei, Ming, et al.
Publicado: (2025)

Implementation of Entanglement Witnesses with Quantum Circuits
por: Shu‐Qian Shen, et al.
Publicado: (2024)

Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity
por: Qu, Jiaming, et al.
Publicado: (2026)

Code-Switched Language Identification is Harder Than You Think
por: Burchell, Laurie, et al.
Publicado: (2024)

Flow on Social Media? Rarer Than You'd Think
por: Knierim, Michael T., et al.
Publicado: (2026)

Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs
por: Zhu, Wenhui, et al.
Publicado: (2026)

Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Training Framework
por: Tang, Wenhao, et al.
Publicado: (2025)

AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
por: Gao, Shanghua, et al.
Publicado: (2026)

GridFormer: Point-Grid Transformer for Surface Reconstruction
por: Li, Shengtao, et al.
Publicado: (2024)