Multi-Bandwidth Distribution Matching Distillation: On the Equivalence of Distribution Matching Distillation and Drifting Models

arXiv:2610.10989 · cs.LG, cs.CV · Submitted 2026-10-07 · Read on arXiv

cs.LG, cs.CV

Submitted: 2026-10-07

Updated: 2026-10-07

Terminology

• Distillation — 45× in this paper · explained in 2 episodes
• Flow Matching — 35× in this paper · explained in 7 episodes
• Distribution Matching — 30× in this paper · explained in 2 episodes
• Distribution Matching Distillation — 25× in this paper
• Diffusion Model — 16× in this paper · explained in 8 episodes
• Multi-Bandwidth Distribution Matching Distillation — 15× in this paper
• Diffusion Models — 8× in this paper · explained in 6 episodes
• Score Function — 8× in this paper · explained in 4 episodes
• Generative Model — 6× in this paper · explained in 2 episodes
• Generative Modeling — 4× in this paper · explained in 3 episodes
• Curse of Dimensionality — 3× in this paper · explained in 6 episodes
• Generative Models — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Optimal Transport — 2× in this paper · explained in 5 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Alignment Problem — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Diffusion Processes — 1× in this paper · explained in 2 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Mixture-of-Experts (MoE) — 1× in this paper · explained in 7 episodes
• Model Variance Preservation — 1× in this paper
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Signal-to-Noise Ratio — 1× in this paper
• Signal-to-noise ratio (SNR) — 1× in this paper · explained in 2 episodes
• Variance Exploding — 1× in this paper

Sources

• Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning
• Generative Modeling via Drifting
• Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals
• SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation
• One-Step Generative Modeling via Wasserstein Gradient Flows
• Reinforcing Few-step Generators via Reward-Tilted Distribution Matching
• 1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation
• A Long-Short Flow-Map Perspective for Drifting Models
• Flow Matching for Generative Modeling
• Flow Matching Guide and Code
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• Denoising Diffusion Implicit Models
• Score-Based Generative Modeling through Stochastic Differential Equations
• Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective
• Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
• Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks