V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising
- 10 September 2026
- book chapter
- Published by Springer Nature
- p. 380-398
Abstract
No abstract availableKeywords
This publication has 14 references indexed in Scilit:
- REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers2025
- Unified Dense Prediction of Video Diffusion2025
- Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models2025
- Simpler Diffusion: 1.5 FID on ImageNet512 with pixel-space diffusion2025
- U-REPA: Aligning Diffusion U-Nets to ViTs2025
- SiT: Exploring Flow and Diffusion-Based Generative Models with Scalable Interpolant Transformers2024
- Scalable Diffusion Models with Transformers2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution2016
- ImageNet: A large-scale hierarchical image database2009