arXiv:2606. 11075v1 Announce Type: new Abstract: Aligning text-to-image flow matching models with human preferences via direct reward backpropagation is sample-efficient but hampered by two well-known pathologies: activations cannot be stored across the full sampling trajectory at modern model scale, and chained Jacobian products across steps inflate the reward gradient as it travels back to early indices.
By Ruoyu Wang, Boye Niu, Xiangxin Zhou, Yushi Huang, Tongliang Liu, Chi Zhang
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:2608.23664v1 Announce Type: cross
Abstract: Reward fine-tuning is becoming an important tool for adapting diffusion models to human preferences and task-specific objectives, but existing method...
By Jaemoo Choi, Wei Guo, Yuchen Zhu, Arash Vahdat, Molei Tao, Julius Berner, Yongxin Chen
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
arXiv:2604. 27147v3 Announce Type: replace-cross Abstract: In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as \textit{guidance}.
By Jerry Y. Huang, Justin Lin, Sheel Shah, Kartik Nair, Nicholas M. Boffi
arXiv:2601. 14430v2 Announce Type: replace-cross Abstract: Controlling generative models is computationally expensive.
By Peter Potaptchik, Adhi Saravanan, Abbas Mammadov, Alvaro Prat, Michael S. Albergo, Yee Whye Teh
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
CAST introduces a reinforcement‑learning fine‑tuning framework for diffusion models that addresses three key limitations: it automatically selects the denoising window based on each model’s trajectory, decomposes prompts into verifiable semantic atoms via Causal Scene Graphs, and applies atom‑level rewards spatially weighted in the policy objective. The method is applied to FLUX.2‑dev and Qwen‑Image‑2512, yielding up to 3.07× improvement on the hardest GenEval 2 prompts compared with Flow‑GRPO while also enhancing overall generation quality.
By Shu Yu, Chaochao Lu
VaLoP introduces a new method for reward-guided diffusion called Value Gradient Lookahead and Pullback, which evaluates the value function at a less noisy state and pulls its gradient back to the current state to reduce posterior covariance errors. The approach unifies two common gradient estimators and adds a correction term computed with a single vector-Jacobian product, while VaLoP‑Fast amortizes this correction with a lightweight head trained on a single reward. Experiments across multiple models, rewards, and datasets show that both variants consistently outperform existing value‑gradient guidance, and VaLoP‑Fast achieves the highest success rates on robot policy benchmarks such as LIBERO and RoboCasa.
By Kwanyoung Kim
The paper introduces Diffusion LAIR, a listwise preference optimization technique that leverages continuous reward scores instead of binary pairwise comparisons to align text‑to‑image diffusion models. LAIR transforms reward scores into centered advantage weights and optimizes an advantage‑weighted regression objective on an implicit reward defined by denoising‑loss improvement over a reference model, with a quadratic penalty to regulate reward magnitude. Experiments demonstrate that Diffusion LAIR surpasses strong baseline methods on SD1.5 and SDXL across generation, compositional, and editing tasks.
By Austin Wang, Jiaqi Han, Stefano Ermon, Yisong Yue
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
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