What kills v-prediction? A Patch-wise PCA Perspective on Pixel-Space Flow Matching
cs.CV, cs.LG
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/THUMAI-Lab/RiT
Terminology
Sources
- Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
- Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
- PixelFlow: Pixel-Space Generative Models with Flow
- DiP: Taming Diffusion Models in Pixel Space
- CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
- Classifier-Free Diffusion Guidance
- Auto-Encoding Variational Bayes
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- Back to Basics: Let Denoising Generative Models Denoise
- 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
- Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
- Wan: Open and Advanced Large-Scale Video Generative Models
- PixNerd: Pixel Neural Field Diffusion
- PixelDiT: Pixel Diffusion Transformers for Image Generation
- Diffusion Transformers with Representation Autoencoders
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs