AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

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

Han Lin, Xichen Pan, Zun Wang, Yue Zhang, Chu Wang, Jaemin Cho, Mohit Bansal

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use fully dual-stream architecture instead of shared-backbone token concatenation (ablation)V-Co co-denoising JiT-B/16 · ImageNet-256 (200 ep, CFG=1.0)FID: 14.70 -> 8.86Improved
allocate more feature-specific blocks in token-concat single-stream (2 to 6) (ablation)single-stream TokenConcat · ImageNet-256 (200 ep, CFG=1.0)FID: 14.70 -> 12.35Improved
use token concatenation instead of direct addition for fusion (ablation)single-stream JiT-B/16 · ImageNet-256 (200 ep, CFG=1.0)FID: 15.15 -> 14.70Improved
add co-denoising with Latent Forcing-style single-stream over plain JiT-B/16JiT-B/16 · ImageNet-256 (200 ep, CFG=1.0)FID: 32.54 -> 13.06Improved
use structural semantic-to-pixel masking instead of zero-embedding dropout for unconditional CFG (ablation)V-Co dual-stream · ImageNet-256 (200 ep, CFG=2.9, independent dropout)FID: 6.69 -> 3.59Improved
use semantic-to-pixel mask only instead of bidirectional cross-stream mask (ablation)V-Co dual-stream · ImageNet-256 (200 ep, CFG=2.9, joint dropout)FID: 5.66 -> 3.18Improved
use joint dropout of labels and semantic features instead of zero-embedding independent dropout (ablation)V-Co with semantic-to-pixel mask · ImageNet-256 (200 ep, CFG=2.9)FID: 3.59 -> 3.18Improved
jointly drop labels and semantic features with input-level zero embedding (ablation)V-Co without structural mask · ImageNet-256 (200 ep, CFG=2.9)FID: 6.69 -> 24.75Hurt
add perceptual-drifting hybrid loss to V-Co (ablation)V-Co-B/16 · ImageNet-256 (300 ep, guided)FID: 2.96 -> 2.44Improved
add REPA loss on top of co-denoising (ablation)V-Co-B/16 · ImageNet-256 (300 ep, guided)FID: 2.96 -> 2.91No clear effect
add RMS-based feature rescaling of semantic features (ablation)V-Co-B/16 · ImageNet-256 (200 ep, guided)FID: 5.28 -> 2.52Improved
use RMS scaling instead of noise-schedule shifting (ablation)V-Co-B/16 · ImageNet-256 (200 ep, guided)FID: 2.93 -> 2.52Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy