Improved Distributional Diffusion Models
cs.CV, cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/CompVis/iDDM
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Demystifying MMD GANs
- Generative Modeling via Drifting
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
- One-Step Generative Modeling via Wasserstein Gradient Flows
- Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs)
- REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- Back to Basics: Let Denoising Generative Models Denoise
- Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
- Movie Gen: A Cast of Media Foundation Models
- Meta Flow Maps enable scalable reward alignment
- High-Resolution Image Synthesis with Latent Diffusion Models
- GLU Variants Improve Transformer
- Reverse Markov Learning: Multi-Step Generative Models for Complex Distributions
- Three-Body Scattering for Generative Modeling
- Diffuse and Disperse: Image Generation with Representation Regularization
- Representation Fr'echet Loss for Visual Generation
- Diffusion Transformers with Representation Autoencoders
- Terminal Velocity Matching
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