Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion

arXiv:2609.36014 · cs.CV · Submitted 2026-09-28 · Read on arXiv

cs.CV

Submitted: 2026-09-28

Updated: 2026-09-28

Project page: https://chongwang1024.github.io/PerF

Terminology

• Transformer — 40× in this paper · explained in 2 episodes
• Diffusion Model — 23× in this paper · explained in 8 episodes
• Diffusion Models — 20× in this paper · explained in 6 episodes
• Alignment — 18× in this paper · explained in 1 episode
• Persistence Guidance — 13× in this paper
• Ablation — 6× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 6× in this paper
• Generative Model — 4× in this paper · explained in 2 episodes
• Generative Models — 4× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Generative Modeling — 3× in this paper · explained in 3 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Latent Diffusion Model — 2× in this paper · explained in 2 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Latent Representation — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation
• PixelFlow: Pixel-Space Generative Models with Flow
• Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion
• Improving Flexible Image Tokenizers for Autoregressive Image Generation
• A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples
• Adaptive Computation Time for Recurrent Neural Networks
• PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion
• Classifier-Free Diffusion Guidance
• Scalable Adaptive Computation for Iterative Generation
• PixelGen: Improving Pixel Diffusion with Perceptual Supervision
• Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
• Representation Alignment for Just Image Transformers is not Easier than You Think
• Variable-Width Transformers

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