UniEdit-Flow presents tuning-free Uni-Inv and Uni-Edit methods for inversion and editing in flow models that achieve accurate reconstruction and robust region-preserving edits across generative models.
Stochastic sampling from deterministic flow models.arXiv preprint arXiv:2410.02217
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
verdicts
UNVERDICTED 9representative citing papers
BayesFP provides a unified retraining-free sampler for diffusion and flow policies by casting constrained trajectory generation as posterior sampling via an extended Feynman-Kac corrector.
Introduces a path-space stochastic control formulation for diffusion posterior sampling with time reparameterization and trust-region optimization to achieve more accurate sampling and importance-weighted corrections.
GenSBI delivers JAX-native implementations of generative SBI methods with transformer backbones and reports near-ideal calibration scores on standard benchmarks.
FM4PDE applies flow matching to learn joint PDE coefficient-solution distributions, using guided sampling with composite losses for forward and inverse problems and providing error guarantees under stated assumptions.
StreamEdit enables high-quality training-free video editing by adapting streaming video generation models with dual-branch fast sampling, self-attention bridge, cross-attention grounding, source-oriented guidance, and visual prompting, outperforming prior methods in few-step regimes.
Flow-Direct constructs a reusable non-parametric guidance field from the log-density ratio of base and target distributions using all accumulated reward samples for feedback-efficient guidance in flow models.
Latent Stochastic Interpolants jointly optimize encoder-decoder and a latent-space stochastic interpolant using a continuous-time ELBO to transform arbitrary priors into aggregated posteriors.
Emyx, a compact flow matching model with EDM reparametrization, outperforms larger protein generators on enzyme design benchmarks with substantially lower training compute.
citing papers explorer
-
UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models
UniEdit-Flow presents tuning-free Uni-Inv and Uni-Edit methods for inversion and editing in flow models that achieve accurate reconstruction and robust region-preserving edits across generative models.
-
BayesFP: Posterior Estimation for Flow-Based Policies via Feynman-Kac Sampling
BayesFP provides a unified retraining-free sampler for diffusion and flow policies by casting constrained trajectory generation as posterior sampling via an extended Feynman-Kac corrector.
-
A Stabilized Path-Space Approach to Diffusion-Based Posterior Sampling
Introduces a path-space stochastic control formulation for diffusion posterior sampling with time reparameterization and trust-region optimization to achieve more accurate sampling and importance-weighted corrections.
-
GenSBI: Generative Methods for Simulation-Based Inference in JAX
GenSBI delivers JAX-native implementations of generative SBI methods with transformer backbones and reports near-ideal calibration scores on standard benchmarks.
-
Guided Flow Matching for Forward and Inverse PDE Problems with Sparse Observations: Algorithm and Theory
FM4PDE applies flow matching to learn joint PDE coefficient-solution distributions, using guided sampling with composite losses for forward and inverse problems and providing error guarantees under stated assumptions.
-
StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation
StreamEdit enables high-quality training-free video editing by adapting streaming video generation models with dual-branch fast sampling, self-attention bridge, cross-attention grounding, source-oriented guidance, and visual prompting, outperforming prior methods in few-step regimes.
-
Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
Flow-Direct constructs a reusable non-parametric guidance field from the log-density ratio of base and target distributions using all accumulated reward samples for feedback-efficient guidance in flow models.
-
Latent Stochastic Interpolants
Latent Stochastic Interpolants jointly optimize encoder-decoder and a latent-space stochastic interpolant using a continuous-time ELBO to transform arbitrary priors into aggregated posteriors.
-
Emyx: Fast and efficient all-atom protein generation
Emyx, a compact flow matching model with EDM reparametrization, outperforms larger protein generators on enzyme design benchmarks with substantially lower training compute.