FlowADMM replaces stochastic renoise-denoise steps in flow-based plug-and-play methods with a deterministic expectation operator inside ADMM, yielding convergence guarantees under weak Lipschitz conditions and state-of-the-art results on standard inverse problems.
D-Flow: Differen- tiating through Flows for Controlled Generation, July 2024
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 3
baseline 1
citation-polarity summary
representative citing papers
LENS shapes low-frequency eigen noise with a lightweight network to enable efficient, high-quality sampling in distilled diffusion models.
DDE introduces a compact coordinator network that combines denoised outputs from pre-trained diffusion models to enable generation in larger domains and complex conditioning settings.
GenMed uses diffusion models to capture P(X,Y) for medical tasks and performs inference via gradient-based test-time optimization, supporting arbitrary observation combinations without retraining.
FMPlug adapts foundation flow-matching models into practical priors for inverse problems by combining instance-guided warm-start with sharp Gaussianity regularization, showing superior results on image restoration and scientific tasks with limited samples.
Diffusion models improve generation quality via inference-time search over noise candidates guided by verifiers and algorithms, yielding gains beyond denoising step scaling on class- and text-conditioned benchmarks.
citing papers explorer
-
FlowADMM: Plug-and-play ADMM with Flow-based Renoise-Denoise Priors
FlowADMM replaces stochastic renoise-denoise steps in flow-based plug-and-play methods with a deterministic expectation operator inside ADMM, yielding convergence guarantees under weak Lipschitz conditions and state-of-the-art results on standard inverse problems.
-
LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling
LENS shapes low-frequency eigen noise with a lightweight network to enable efficient, high-quality sampling in distilled diffusion models.
-
Diffusion Domain Expansion: Learning to Coordinate Pre-trained Diffusion Models
DDE introduces a compact coordinator network that combines denoised outputs from pre-trained diffusion models to enable generation in larger domains and complex conditioning settings.
-
GenMed: A Pairwise Generative Reformulation of Medical Diagnostic Tasks
GenMed uses diffusion models to capture P(X,Y) for medical tasks and performs inference via gradient-based test-time optimization, supporting arbitrary observation combinations without retraining.
-
Saving Foundation Flow-Matching Priors for Inverse Problems
FMPlug adapts foundation flow-matching models into practical priors for inverse problems by combining instance-guided warm-start with sharp Gaussianity regularization, showing superior results on image restoration and scientific tasks with limited samples.
-
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
Diffusion models improve generation quality via inference-time search over noise candidates guided by verifiers and algorithms, yielding gains beyond denoising step scaling on class- and text-conditioned benchmarks.
- How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance