LDM-is-AE: Latent Diffusion Model is an Auto-Encoder for End-to-End Image Generation
cs.CV
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/PolyU-VCLab/LDMisAE
Terminology
Sources
- FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
- Masked Autoencoders Are Effective Tokenizers for Diffusion Models
- BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
- PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
- Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
- PixelFlow: Pixel-Space Generative Models with Flow
- End-to-End Training for Unified Tokenization and Latent Denoising
- Back to Basics: Let Denoising Generative Models Denoise
- DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
- DINOv2: Learning Robust Visual Features without Supervision
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- Latent Diffusion Model without Variational Autoencoder
- DINOv3
- Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?
- PixNerd: Pixel Neural Field Diffusion
- DDT: Decoupled Diffusion Transformer
- Diffusion As Self-Distillation: End-to-End Latent Diffusion In One Model
- Qwen3 Technical Report
- Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
- Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
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