Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation
cs.LG, cs.CV
Submitted: 2026-05-30
Updated: 2026-11-02
Code: https://github.com/Genentech/semantic-transport-generation
Terminology
Sources
- Deep ViT Features as Dense Visual Descriptors
- stable-pretraining-v1: Foundation Model Research Made Simple
- VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models
- AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models
- Generative Modeling via Drifting
- One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation
- Auto-Encoding Variational Bayes
- There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training
- REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
- Entropic estimation of optimal transport maps
- High-Resolution Image Synthesis with Latent Diffusion Models
- DINOv3
- What matters for Representation Alignment: Global Information or Spatial Structure?
- Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
- Diffuse and Disperse: Image Generation with Representation Regularization
- REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
- Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
- Diffusion Transformers with Representation Autoencoders
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning