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×.
By Abbas Mammadov, Jerry Y. Huang, Justin Lin, Partha Kaushik, Sheel Shah, Kartik Nair, Yee Whye Teh, Nicholas M. Boffi
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...
By Hongeun Kim, Jeongsol Kim, Jong Chul Ye
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...
By Chi Zhang, Shi Haoyang, Yueyi Liu, Ruichuan An, Junkang Zhou, Chang Li, Xiuyuan Lu, Yichi Zhang, Bo Wang, Yuhang Wu, Sen Cui, Miao Liu
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.
By Ruihang Li, Mengde Xu, Shuyang Gu, Leigang Qu, Fuli Feng, Han Hu, Wenjie Wang
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...
By Zhengyi Guo, Jiayuan Sheng, Wenpin Tang, David D. Yao
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.
By Woocheol Shin, Taeyoung Yun, Jiwon Sung, Hyeongyu Kang, Jeongmin Park, Jaewoo Lee, Kyuil Sim, Dohyun Kim, Yutong He, Jinkyoo Park
The paper introduces ZeNOVA, a gradient‑free method for aligning initial noise in generative models. It uses annealed soft‑value guidance, manifold‑constrained hyperspherical Langevin dynamics, and Metropolis‑Hastings jumps to address instability in black‑box reward settings. Experiments on image and video models show ZeNOVA outperforms existing zeroth‑order baselines by more stably optimizing noise toward higher rewards.
By Jinho Chang, Jong Chul Ye
Fenchel Tilt Flow Control (FTFC) is a new method for fine‑tuning pretrained generative models to arbitrary preference functions. It decouples utility optimization from model fitting by first learning reward and density‑ratio weights on pretrained samples, then freezing these weights to adjust a diffusion or flow model in a single importance‑weighted stage. The approach supports general f‑divergence penalties, achieves exact duality for concave utilities, and demonstrates up to 20× efficiency gains while outperforming baselines on image and molecule generation tasks.
By Maksim Bobrin, Maksim Zhdanov, Dmitry Dylov
The paper introduces DM-Align, a single-stage optimization framework that jointly performs distribution matching for distillation and aligns video generative models with human preferences. By deriving complementary gradient directions—one minimizing the gap between real and fake models and another guiding the model toward preferred samples—the method eliminates the need for separate reinforcement learning and distillation stages. Experiments on multiple foundational video models show that this sample-guided approach consistently outperforms both standalone variants and traditional two-stage pipelines.
By Jiuzhou Lin, Junlong Wu, Fei Zuo, Huan Ouyang, Dewen Fan, Boheng Zhang, Huaiqing Wang, Jia Sun, Fan Yang, Houde Liu, Kehai Chen, Min Zhang, Tingting Gao, Han Li
The paper presents a new one‑step generative modeling framework for finite state spaces, leveraging discrete Wasserstein geometry to define a target‑relative KL gradient flow over a reversible Markov kernel. The authors implement this flow at the particle level using Markov jumps and encode the resulting transport updates into a latent‑conditioned generator, enabling one‑step inference after training. Experiments on a controlled setting confirm KL dissipation, consistency between particle dynamics and probability flow, and accurate numerical scaling, while a finite‑capacity neural generator successfully tracks the exact transport targets.
By Alessandro Micheli, Andrea Zerio, Samir Bhatt
Recent advances in distillation and flow-map models have enabled deterministic one- or few-step generation for high-quality data, facilitating a new branch of reward alignment approaches that directly...
arXiv:2608.21425v1 Announce Type: cross
Abstract: Video generation is central to AI-powered content creation. Aligning generated videos with human preferences is a key criterion for evaluating genera...
By Nai-Xin Zhai, Weihua Cheng, Dexu Yu, Yikai Gu, Hanwen Du, Junchen Fu, Chenxi Huang, Yingwei Song, Liyuan Lillian Ma, Yang Ran, Youhua Li, Yongxin Ni