V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising

arXiv:2603.16792 · cs.CV, cs.AI · Submitted 2026-03-17 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-03-17

Updated: 2026-08-31

Comments: Accepted by ECCV 2026. code: https://github.com/HL-hanlin/V-Co

Code: https://github.com/HL-hanlin/V-Co

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 32× in this paper · explained in 1 episode
• Diffusion Model — 19× in this paper · explained in 8 episodes
• Calibration — 15× in this paper · explained in 7 episodes
• Transformer — 14× in this paper · explained in 2 episodes
• Ablation — 13× in this paper · explained in 1 episode
• Diffusion Models — 13× in this paper · explained in 6 episodes
• Dual-Stream Architecture — 9× in this paper · explained in 3 episodes
• Generative Model — 7× in this paper · explained in 2 episodes
• Generative Models — 6× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Latent Space — 3× in this paper · explained in 7 episodes
• Regularization — 3× in this paper · explained in 3 episodes
• Semantic Alignment — 3× in this paper · explained in 3 episodes
• Signal-to-noise ratio (SNR) — 3× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Latent Diffusion Model — 2× in this paper · explained in 2 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Unified Framework — 2× in this paper · explained in 5 episodes
• Alignment Methods — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 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
• Mode Collapse — 1× in this paper · explained in 2 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Variational Bayes — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation
• Motus: A Unified Latent Action World Model
• Hyperspherical Autoencoder for High-Fidelity Image Reconstruction and Generation
• PixelFlow: Pixel-Space Generative Models with Flow
• UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation
• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Back to Basics: Let Denoising Generative Models Denoise
• Fractal Generative Models
• One-step Latent-free Image Generation with Pixel Mean Flows
• DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
• PixelGen: Improving Pixel Diffusion with Perceptual Supervision
• DINOv2: Learning Robust Visual Features without Supervision
• DiP: Taming Diffusion Models in Pixel Space
• SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis
• Generative Modeling via Drifting
• TV2TV: A Unified Framework for Interleaved Language and Video Generation
• MeanFlow Transformers with Representation Autoencoders
• PixelDiT: Pixel Diffusion Transformers for Image Generation
• 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