The paper introduces Objective-aware Trajectory Credit Assignment (OTCA), a framework that refines reinforcement learning for diffusion-based visual generation. OTCA decomposes credit across denoising steps and allocates multiple reward signals adaptively, addressing the coarse, uniform reward assignment of existing GRPO pipelines. Experiments demonstrate that OTCA consistently enhances image and video generation quality across various metrics.
By Rui Li, Ke Hao, Yuanzhi Liang, Haibin Huang, Chi Zhang, Yun Gu, Xuelong Li
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
arXiv:2609.30840v1 Announce Type: cross
Abstract: One-step generators enable high-quality visual generation with a single network evaluation, but their post-training is difficult: general implicit ge...
By Austin Wang, Ziheng Cheng, Lexing Ying
arXiv:2603. 23086v2 Announce Type: replace Abstract: Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and diversity.
By Orhun Bugra Baran, Melih Kandemir, Ramazan Gokberk Cinbis
arXiv:2604. 16557v2 Announce Type: replace Abstract: Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL).
By Yuming Yan, Kai Tang, Sihong Chen, Ke Xu, Dan Hu, Qun Yu, Pengfei Hu
arXiv:2601. 12401v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human preferences and user-specified tasks.
By Jinmei Liu, Haoru Li, Zhenhong Sun, Chaofeng Chen, Yatao Bian, Bo Wang, Daoyi Dong, Chunlin Chen, Zhi Wang
arXiv:2603. 12893v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt alignment.
By David McAllister, Miika Aittala, Tero Karras, Janne Hellsten, Angjoo Kanazawa, Timo Aila, Samuli Laine
arXiv:2608.29647v1 Announce Type: new
Abstract: To mitigate the time complexity of generative models, one-step generative models have recently emerged through direct mapping from noise to data in a s...
By Hoseong Hwang, Woorim Han, Joungin Chun, Jinseong Park, Jaewoong Choi
arXiv:2607. 00691v1 Announce Type: new Abstract: Black-box optimization is a fundamental science and engineering tool that makes it possible to optimize objectives without gradient information.
By Edouard R. Dufour, Pascal Fua
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
The paper introduces Reflection-Aware GRPO (RA‑GRPO), a reinforcement‑learning framework that aligns diffusion generative models with human preferences. It uses Diffusion Reflection to correct intermediate sampling paths by reversing the diffusion process, and Counterfactual Path Synthesis to embed these corrected trajectories into the policy, avoiding extra inference cost. Experiments on text‑to‑image and text‑to‑video models show RA‑GRPO outperforms existing methods, reducing reward hacking and improving generalization while remaining architecture‑agnostic.
By Junlong Wu, Jiuzhou Lin, Jia Sun, Boheng Zhang, Huaiqing Wang, Dewen Fan, Houde Liu, Qianqian Gan, Fan Yang, Tingting Gao
arXiv:2606. 02521v1 Announce Type: new Abstract: One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization.
By Zhou Jiang, Yandong Wen, Zhen Liu