arXiv Machine Learning
Reward-guided Fine-Tuning of One-Step Generative Models via Wasserstein Gradient Flow
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Sep 24
WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps
The paper introduces Wasserstein‑Tilted Flow Maps (WTF), a simulation‑free reinforcement learning method that fine‑tunes pre‑trained flow‑based generative models by adding an optimal transport regularizer derived from the model’s drift. Unlike traditional KL‑reward tilting, WTF transports individual samples toward higher reward, framing the problem as a deterministic optimal control task on the flow map. Experiments on ImageNet‑256 and text‑to‑image demonstrate that WTF achieves higher reward and comparable or better diversity while reducing training compute by up to 280×.
arXiv Machine Learning
1d ago
Learning Noise Optimization for Reward Alignment in Few-Step Generative Models
arXiv:2611.06255v1 Announce Type: new Abstract: Reward alignment for diffusion- and flow-based generative models is often formulated over stochastic trajectories, making it less suitable for few-step...
arXiv Machine Learning
Oct 2
Unifying Distributional Training for One-Step Visual Generation
arXiv:2609.35763v3 Announce Type: replace Abstract: Distributional training provides collective supervision for one-step visual generation by matching real and generated features in frozen representa...
arXiv Machine Learning
Jul 3
Optimizing Visual Generative Models via Distribution-wise Rewards
arXiv:2607. 02291v1 Announce Type: new Abstract: Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degrades image diversity and introduces visual anomalies.
arXiv AI
Oct 2
DOHF: Online Diffusion Fine-tuning with Doob's $h$-transform Guidance
arXiv:2609.31882v2 Announce Type: replace-cross Abstract: Reward-based diffusion fine-tuning faces practical challenges when desirable outcomes are rare or conditioning corrections are costly to esti...
arXiv Machine Learning
Oct 16
Noise-Space Reward Alignment for Few-Step Generative Models
The paper introduces Noise Policy Optimization (NPO), a method for aligning few-step generative models with black-box reward signals. NPO learns an amortized flow policy that transforms initial Gaussian noise into a reward-tilted distribution, allowing the pretrained generator to produce higher-reward outputs without fine-tuning. The approach achieves superior reward-quality trade-offs across image, language, and protein generation tasks while drastically reducing inference cost compared to test-time search methods.