Diffusion Models
Overview
Diffusion models learn a data distribution by gradually corrupting examples with noise and training a denoiser to reverse that process. Major approaches include DDPMs and score-based SDEs, latent diffusion and diffusion Transformers, flow and consistency methods, and discrete masked or continuous-time Markov diffusion; conditioning and guidance adapt them to specific tasks. They are used for images, video, audio, language, molecules, and scientific forecasting, with evaluations ranging from ImageNet FID to language perplexity and domain-specific measures of accuracy and uncertainty. A central tension is how to make sampling faster and generation more controllable without sacrificing quality, calibration, or diversity, while theory and ongoing audits address generalization, memorization, and privacy.
Latest papers
1,278 papers90 papers in the last four weeks, down 44% on the four weeks before. 0.7% of all new papers.
Identifiable World Models from Pretrained Diffusion Representations
No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models
Hybrid-Basis Feature Forecasting for Diffusion Sampling Acceleration
Cross-Time Directional Selection in Diffusion Sampling
How corner is a corner case? Percentile control for highway scenario generation
EDISCO: Equivariant DIScrete Diffusion for Euclidean Combinatorial Optimization
Backward-Consistent Diffusion Sampling for Sparsely Observed PDE Inverse Problems
FASTER: Fast Adjoint Stochastic Transport for Endpoint Refinement in Reward-Guided Image Editing
ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Caching
Discrete Diffusion for Large Graph Generation via Structural Candidate Restriction
Depth as Time in One-Step Generative Models
SiT-L/2 model can be compressed by in parameters into a single time-conditioned block. We offer an explanation for this denoise-then-renoise behavior and show that, when we treat the layerwise computation explicitly as a flow, a single time-conditioned block can be trained to denoise across layers, compressing a MeanFlow SiT-L/2 model by in parameters. Together, these results suggest that the temporal computation of diffusion is not eliminated by one-step generation, but reorganized across network depth.