REVIEW 16 cited by
Optimizing DDPM Sampling with Shortcut Fine-Tuning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Optimizing DDPM Sampling with Shortcut Fine-Tuning
read the original abstract
In this study, we propose Shortcut Fine-Tuning (SFT), a new approach for addressing the challenge of fast sampling of pretrained Denoising Diffusion Probabilistic Models (DDPMs). SFT advocates for the fine-tuning of DDPM samplers through the direct minimization of Integral Probability Metrics (IPM), instead of learning the backward diffusion process. This enables samplers to discover an alternative and more efficient sampling shortcut, deviating from the backward diffusion process. Inspired by a control perspective, we propose a new algorithm SFT-PG: Shortcut Fine-Tuning with Policy Gradient, and prove that under certain assumptions, gradient descent of diffusion models with respect to IPM is equivalent to performing policy gradient. To our best knowledge, this is the first attempt to utilize reinforcement learning (RL) methods to train diffusion models. Through empirical evaluation, we demonstrate that our fine-tuning method can further enhance existing fast DDPM samplers, resulting in sample quality comparable to or even surpassing that of the full-step model across various datasets.
Forward citations
Cited by 16 Pith papers
-
Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline
A new adjoint matching framework formulates flow model alignment as optimal control, enabling direct regression training and terminal-trajectory truncation for efficiency gains on models like SiT-XL and FLUX.
-
Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation
OTCA improves GRPO training for visual generation by estimating step importance in trajectories and adaptively weighting multiple reward objectives.
-
MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
MixGRPO speeds up GRPO for flow-based image generators by restricting SDE sampling and optimization to a sliding window while using ODE elsewhere, cutting training time by up to 71% with better alignment performance.
-
Optimizing Visual Generative Models via Distribution-wise Rewards
Distribution-wise rewards with subset-replace strategy and post-hoc merging improve FID-50K on SiT (8.30 to 5.77) and EDM2 (3.74 to 3.52) while preserving diversity.
-
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
CACFM applies RL to adaptively select critical regions in probability flow ODE trajectories for consistency distillation, yielding SOTA few-step results on FLUX and SDXL.
-
V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think
V-GRPO makes ELBO surrogates stable and efficient for online RL alignment of denoising models, delivering SOTA text-to-image performance with 2-3x speedups over MixGRPO and DiffusionNFT.
-
NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control
NaP-Control uses RL to directly predict optimized diffusion noise from a task-agnostic prior, enabling fast inference and higher success rates for versatile whole-body character control while preserving motion quality.
-
Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach
By adding drift g(t)^2 ∇log h(t,y) with h estimated via martingale and covariation losses, diffusion samples can be hard-conditioned on an event.
-
Seeing What Matters: Visual Preference Policy Optimization for Visual Generation
ViPO enhances GRPO for visual generation by creating spatially and temporally aware advantage maps from pretrained vision models to focus optimization on perceptually important regions.
-
Diffusion Policy Policy Optimization
DPPO fine-tunes diffusion policies via policy gradients and outperforms prior RL approaches for diffusion policies and PG-tuned alternatives on robot benchmarks while enabling stable training and hardware deployment.
-
Training Diffusion Models with Reinforcement Learning
DDPO uses policy gradients on the denoising process to optimize diffusion models for arbitrary rewards like human feedback or compressibility.
-
PAPA: Online Personalized Active Preference Alignment
PAPA directly optimizes diffusion models via real-time user feedback for personalized preference alignment, drawing from variational inference, with an efficiency-enhanced variant EPAPA.
-
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.
-
Embedding-perturbed Exploration Preference Optimization for Flow Models
E²PO uses embedding-level perturbations to maintain intra-group variance and discriminative signal in RL-based preference optimization for generative flow models.
-
NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control
A latent-noise navigation policy trained with RL steers a frozen diffusion character-control prior, achieving fast and robust task execution without test-time guidance.
-
PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
A data-generation pipeline plus pairwise subject-consistency rewards in RL improve consistency and prompt adherence for multi-subject personalized image generation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.