Balancing Frequencies and Pixels in Flow Matching
cs.CV
Submitted: 2026-09-02
Updated: 2026-10-13
Terminology
Sources
- PixelFlow: Pixel-Space Generative Models with Flow
- DiP: Taming Diffusion Models in Pixel Space
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
- Back to Basics: Let Denoising Generative Models Denoise
- Decoupled Weight Decay Regularization
- DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
- PixelGen: Improving Pixel Diffusion with Perceptual Supervision
- Frequency-Aware Flow Matching for High-Quality Image Generation
- A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines
- SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
- PixelDiT: Pixel Diffusion Transformers for Image Generation
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