Introduces a marginal-alignment regularizer for reflow distillation of diffusion models that aligns endpoint marginals, supported by a telescoping TV bound and benchmark experiments.
Progressive distillation for fast sampling of diffusion models
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
DiffusionOPD applies online policy distillation from per-task teachers to a unified diffusion student, with a derived closed-form per-step KL objective that unifies SDE and ODE sampling via mean matching.
CCVFM uses an entropic Sinkhorn coreset to induce a closed-form Gaussian mixture source for hierarchical rectified flow matching, then trains a lightweight correction flow on the residual, achieving competitive few-step image generation.
A short teacher-alignment repair stage between structured pruning and one-step distillation yields a 20% pruned one-step generator that improves FID from 3.53 to 3.12 on ImageNet-512 while reducing NFE from 63 to 1.
SOM is an actor-critic algorithm that constructs the target velocity field for one-step MeanFlow policies directly from the Q-function via score estimation and probability flow ODE, achieving claimed SOTA on locomotion tasks with reduced training and inference time.
A hierarchical variational formulation amortizes test-time guidance in diffusion models to achieve strong quality-speed tradeoffs with significantly reduced inference compute.
Reconstruction of global 1.5 km resolution 10 m vector winds in tropical cyclone inner cores from sparse CYGNSS scalar observations using generalized score-based diffusion assimilation plus three TC boundary-layer constraints.
AsymTalker uses temporal reference encoding and asymmetric knowledge distillation to produce identity-consistent talking head videos up to 600 seconds long at 66 FPS.
PRPO is a paragraph-level policy optimization technique that grounds vision-language model reasoning in image content to raise deepfake detection accuracy and reasoning quality.
SharpEuler estimates a sharpness profile via finite differences on calibration trajectories, smooths it, and applies a quantile transform to generate adaptive timestep grids that improve Euler sampling quality in flow matching models at fixed budgets.
BADiff introduces joint training of diffusion models with quality conditioning derived from bandwidth to enable adaptive early-stop sampling that preserves appropriate perceptual quality.
A tutorial that unifies diffusion probabilistic models, score-based generative modeling, and SDE methods by deriving forward and reverse dynamics from a shared Gaussian noising process.
citing papers explorer
-
Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment
Introduces a marginal-alignment regularizer for reflow distillation of diffusion models that aligns endpoint marginals, supported by a telescoping TV bound and benchmark experiments.
-
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
DiffusionOPD applies online policy distillation from per-task teachers to a unified diffusion student, with a derived closed-form per-step KL objective that unifies SDE and ODE sampling via mean matching.
-
Coreset-Induced Conditional Velocity Flow Matching
CCVFM uses an entropic Sinkhorn coreset to induce a closed-form Gaussian mixture source for hierarchical rectified flow matching, then trains a lightweight correction flow on the residual, achieving competitive few-step image generation.
-
Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair
A short teacher-alignment repair stage between structured pruning and one-step distillation yields a 20% pruned one-step generator that improves FID from 3.53 to 3.12 on ImageNet-512 while reducing NFE from 63 to 1.
-
Score-Based One-step MeanFlow Policy Optimization
SOM is an actor-critic algorithm that constructs the target velocity field for one-step MeanFlow policies directly from the Q-function via score estimation and probability flow ODE, achieving claimed SOTA on locomotion tasks with reduced training and inference time.
-
Hierarchical Variational Policies for Reward-Guided Diffusion
A hierarchical variational formulation amortizes test-time guidance in diffusion models to achieve strong quality-speed tradeoffs with significantly reduced inference compute.
-
Global kilometre-scale tropical cyclone inner-core vector winds from sparse scalar CYGNSS observations
Reconstruction of global 1.5 km resolution 10 m vector winds in tropical cyclone inner cores from sparse CYGNSS scalar observations using generalized score-based diffusion assimilation plus three TC boundary-layer constraints.
-
AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation
AsymTalker uses temporal reference encoding and asymmetric knowledge distillation to produce identity-consistent talking head videos up to 600 seconds long at 66 FPS.
-
PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection
PRPO is a paragraph-level policy optimization technique that grounds vision-language model reasoning in image content to raise deepfake detection accuracy and reasoning quality.
-
Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching
SharpEuler estimates a sharpness profile via finite differences on calibration trajectories, smooths it, and applies a quantile transform to generate adaptive timestep grids that improve Euler sampling quality in flow matching models at fixed budgets.
-
BADiff: Bandwidth Adaptive Diffusion Model
BADiff introduces joint training of diffusion models with quality conditioning derived from bandwidth to enable adaptive early-stop sampling that preserves appropriate perceptual quality.
-
A Tutorial on Diffusion Theory: From Differential Equations to Diffusion Models
A tutorial that unifies diffusion probabilistic models, score-based generative modeling, and SDE methods by deriving forward and reverse dynamics from a shared Gaussian noising process.