Scaffold Then Internalize: Representation Injection for Diffusion Transformers

arXiv:2609.35292 · cs.CV, cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Project page: https://jeneveuxpas.github.io/REPI

Terminology

• Transformer — 70× in this paper · explained in 2 episodes
• Alignment — 39× in this paper · explained in 1 episode
• Ablation — 13× in this paper · explained in 1 episode
• Diffusion Model — 7× in this paper · explained in 8 episodes
• Diffusion Models — 7× in this paper · explained in 6 episodes
• Flow Matching — 6× in this paper · explained in 8 episodes
• Ablation Studies — 3× in this paper · explained in 1 episode
• Generative AI — 3× in this paper · explained in 2 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Alignment Methods — 2× in this paper · explained in 1 episode
• Generative Models — 2× in this paper · explained in 2 episodes
• Latent Diffusion Model — 2× in this paper · explained in 2 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Diffusion Process — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 3 episodes
• Exponential Moving Average (EMA) — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Normalizing Flow — 1× in this paper · explained in 3 episodes
• Normalizing Flows — 1× in this paper · explained in 4 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Variational Bayes — 1× in this paper · explained in 2 episodes

Sources

• Building Normalizing Flows with Stochastic Interpolants
• Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
• Classifier-Free Diffusion Guidance
• No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves
• Auto-Encoding Variational Bayes
• Boosting Generative Image Modeling via Joint Image-Feature Synthesis
• REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
• SARA: Semantically Adaptive Relational Alignment for Video Diffusion Models
• AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers
• Improving Visual Representation Alignment Generation with GRPO
• MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training
• Representation Alignment for Just Image Transformers is not Easier than You Think
• LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation
• SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training
• Linformer: Self-Attention with Linear Complexity
• REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
• Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
• Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
• Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers
• VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models