pith. sign in

Variational Flow Maps: Make Some Noise for One-Step Conditional Generation , shorttitle =

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

unclear 1

representative citing papers

How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance

cs.LG · 2026-04-29 · unverdicted · novelty 8.0

FMRG reformulates guidance as deterministic optimal control, deriving a single-trajectory method using the flow map that matches or exceeds baselines on reward-guided generation and inverse problems with 3 NFEs at text-to-image scale.

Consistency Regularised Gradient Flows for Inverse Problems

stat.ML · 2026-05-08 · unverdicted · novelty 5.0

A consistency-regularized Euclidean-Wasserstein-2 gradient flow performs joint posterior sampling and prompt optimization in latent space for efficient low-NFE inverse problem solving with diffusion models.

citing papers explorer

Showing 2 of 2 citing papers.

  • How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance cs.LG · 2026-04-29 · unverdicted · none · ref 57

    FMRG reformulates guidance as deterministic optimal control, deriving a single-trajectory method using the flow map that matches or exceeds baselines on reward-guided generation and inverse problems with 3 NFEs at text-to-image scale.

  • Consistency Regularised Gradient Flows for Inverse Problems stat.ML · 2026-05-08 · unverdicted · none · ref 46

    A consistency-regularized Euclidean-Wasserstein-2 gradient flow performs joint posterior sampling and prompt optimization in latent space for efficient low-NFE inverse problem solving with diffusion models.