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.
arXiv preprint arXiv:2509.25170 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 5years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
FAV aligns few-step generative models by amortizing SVGD updates from reward-tilted sampling into generator parameters via fixed-point regression, requiring only sample access, and shows outperformance on robotics tasks plus scaling on image generators.
The choice of closeness measure in diffusion reward alignment determines the computational primitives and tractable reward classes, with linear exponential tilts sufficing for KL with convex rewards and proximal oracles for Wasserstein with concave or low-dimensional Lipschitz rewards.
IMPFM is a multi-particle flow-map sampling method with sequential posterior sharing and interaction-aware correction that targets a KL-tilted distribution for global exploration in online feedback search.
PG-MAP formulates inference-time alignment as joint MAP optimization over conditioning c and latent z_t via forward-consistency coupling for diffusion and flow-matching models, reporting gains in PickScore and HPS metrics.
citing papers explorer
-
How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance
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.
-
Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference
FAV aligns few-step generative models by amortizing SVGD updates from reward-tilted sampling into generator parameters via fixed-point regression, requiring only sample access, and shows outperformance on robotics tasks plus scaling on image generators.
-
The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives
The choice of closeness measure in diffusion reward alignment determines the computational primitives and tractable reward classes, with linear exponential tilts sufficing for KL with convex rewards and proximal oracles for Wasserstein with concave or low-dimensional Lipschitz rewards.
-
Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search
IMPFM is a multi-particle flow-map sampling method with sequential posterior sharing and interaction-aware correction that targets a KL-tilted distribution for global exploration in online feedback search.
-
PG-MAP: Joint MAP Optimization for Inference-Time Alignment of Diffusion and Flow-Matching Models
PG-MAP formulates inference-time alignment as joint MAP optimization over conditioning c and latent z_t via forward-consistency coupling for diffusion and flow-matching models, reporting gains in PickScore and HPS metrics.