SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation

arXiv:2605.18267 · cs.CV · Submitted 2026-05-18 · Read on arXiv

cs.CV

Submitted: 2026-05-18

Updated: 2026-09-26

Terminology

• Normalizing Flow — 45× in this paper · explained in 3 episodes
• Transformer — 29× in this paper · explained in 2 episodes
• Normalizing Flows — 26× in this paper · explained in 4 episodes
• Diffusion Model — 15× in this paper · explained in 8 episodes
• Diffusion Models — 15× in this paper · explained in 6 episodes
• Regularization — 12× in this paper · explained in 3 episodes
• Generative Model — 9× in this paper · explained in 2 episodes
• Generative Models — 9× in this paper · explained in 2 episodes
• Semantic Representation Compressor — 8× in this paper
• Fidelity — 6× in this paper · explained in 2 episodes
• Latent Space — 6× in this paper · explained in 7 episodes
• Latent Diffusion Model — 5× in this paper · explained in 2 episodes
• Latent Diffusion Models — 5× in this paper · explained in 2 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Robustness — 4× in this paper · explained in 5 episodes
• Ambient Dimension — 3× in this paper · explained in 1 episode
• Transformer Autoregressive Flow — 3× in this paper
• Ablation — 2× in this paper · explained in 1 episode
• Decode — 2× in this paper · explained in 2 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Rectified Flow — 2× in this paper · explained in 3 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Flow Matching — 1× in this paper · explained in 7 episodes
• Inception Score — 1× in this paper
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Structural Constraints — 1× in this paper · explained in 2 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes
• Variational Bayes — 1× in this paper · explained in 2 episodes

Sources

• Normalizing Flows are Capable Generative Models
• STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
• SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows
• Normalizing Flows with Iterative Denoising
• Diffusion Transformers with Representation Autoencoders
• Scalable Adaptive Computation for Iterative Generation
• PixelFlow: Pixel-Space Generative Models with Flow
• PixNerd: Pixel Neural Field Diffusion
• Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion
• JetFormer: An Autoregressive Generative Model of Raw Images and Text
• FARMER: Flow AutoRegressive Transformer over Pixels
• Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
• Autoregressive Image Generation without Vector Quantization
• Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
• Fast Training of Diffusion Models with Masked Transformers
• SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers
• MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
• DDT: Decoupled Diffusion Transformer
• REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion 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