CoVA: Composing VAE Representations for Generative Learning
cs.CV
Submitted: 2026-10-09
Updated: 2026-10-09
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- PixelFlow: Pixel-Space Generative Models with Flow
- DiP: Taming Diffusion Models in Pixel Space
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer
- Classifier-Free Diffusion Guidance
- No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves
- Auto-Encoding Variational Bayes
- REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
- Back to Basics: Let Denoising Generative Models Denoise
- Flow Matching for Generative Modeling
- Decoupled Weight Decay Regularization
- DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
- PixelGen: Improving Pixel Diffusion with Perceptual Supervision
- Generating Images with Sparse Representations
- Denoising Diffusion Implicit Models
- SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training
- PixNerd: Pixel Neural Field Diffusion
- Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
- Exploring Representation-Aligned Latent Space for Better Generation
- Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion 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