DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision
cs.LG, cs.CV
Submitted: 2025-02-11
Updated: 2026-10-29
Comments: Accepted for publication at NeurIPS 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Generalized Energy Based Models
- Towards Principled Methods for Training Generative Adversarial Networks
- Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models
- Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
- TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation
- Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
- One Step Diffusion via Shortcut Models
- Mean Flows for One-step Generative Modeling
- Training Neural Samplers with Reverse Diffusive KL Divergence
- Multistep Consistency Models
- Variational Inference using Implicit Distributions
- Bidirectional Consistency Models
- AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
- Pseudo Numerical Methods for Diffusion Models on Manifolds
- Spectral Normalization for Generative Adversarial Networks
- Multistep Distillation of Diffusion Models via Moment Matching
- Amortised MAP Inference for Image Super-resolution
- Denoising Diffusion Implicit Models
- Consistency Models
- VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillation
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning