Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Sihyun, Kwak, Sangkyung, Jang, Huiwon, Jeong, Jongheon, Huang, Jonathan, Shin, Jinwoo, Xie, Saining
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Adversarial Robustification via Text-to-Image Diffusion Models
di: Choi, Daewon, et al.
Pubblicazione: (2024)

StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment
di: Kim, Younghyun, et al.
Pubblicazione: (2025)

Controllable Human Image Generation with Personalized Multi-Garments
di: Choi, Yisol, et al.
Pubblicazione: (2024)

Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
di: Wu, Ge, et al.
Pubblicazione: (2025)

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

Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction
di: Jang, Huiwon, et al.
Pubblicazione: (2024)

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing
di: Choi, June Suk, et al.
Pubblicazione: (2024)

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

Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion Models
di: Lee, Kyungmin, et al.
Pubblicazione: (2024)

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

Improving Diffusion Models for Authentic Virtual Try-on in the Wild
di: Choi, Yisol, et al.
Pubblicazione: (2024)

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

Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness
di: Jang, Suhyeok, et al.
Pubblicazione: (2024)

SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning
di: Jeon, Byungwoo, et al.
Pubblicazione: (2026)

Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model
di: Won, John, et al.
Pubblicazione: (2025)

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

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

FontAdapter: Instant Font Adaptation in Visual Text Generation
di: Koo, Myungkyu, et al.
Pubblicazione: (2025)

Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling
di: Lee, Kyungmin, et al.
Pubblicazione: (2025)

Visual Representation Learning with Stochastic Frame Prediction
di: Jang, Huiwon, et al.
Pubblicazione: (2024)

MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation
di: Yu, Sihyun, et al.
Pubblicazione: (2025)

ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context
di: Jang, Huiwon, et al.
Pubblicazione: (2025)

Diffusion Transformers with Representation Autoencoders
di: Zheng, Boyang, et al.
Pubblicazione: (2025)

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

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
di: Yu, Sihyun, et al.
Pubblicazione: (2024)

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

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

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

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

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

LVMark: Robust Watermark for Latent Video Diffusion Models
di: Jang, MinHyuk, et al.
Pubblicazione: (2024)

Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance
di: Choi, June Suk, et al.
Pubblicazione: (2025)

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

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
di: Tong, Shengbang, et al.
Pubblicazione: (2026)

FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution
di: Kim, Aro, et al.
Pubblicazione: (2026)

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

Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Models
di: Lee, Jimin, et al.
Pubblicazione: (2026)

Training-Free Representation Guidance for Diffusion Models with a Representation Alignment Projector
di: Zu, Wenqiang, et al.
Pubblicazione: (2026)

Data-Efficient Molecular Generation with Hierarchical Textual Inversion
di: Kim, Seojin, et al.
Pubblicazione: (2024)

Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
di: Tang, Bingda, et al.
Pubblicazione: (2025)