arXiv AI June 2, 2026 By Jeongjae Lee, Jinho Chang, Jeongsol Kim, Jong Chul Ye

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models

arXiv:2604. 17415v3 Announce Type: replace-cross Abstract: Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 5

Latent Reward Registers for Diffusion Preference Alignment

arXiv:2608. 03929v1 Announce Type: new Abstract: Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process.

By Yuanshen Guan, Zipeng Feng, Zhiwei Xiong, Peiqin Sun

llms diffusion reinforcement-learning efficiency benchmarks safety

arXiv AI

Jun 3

How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance

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

diffusion safety

arXiv Computer Vision

6d ago

Aligning One-Step Generative Models with Reward-Weighted Transport Distillation

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

efficiency safety

arXiv Machine Learning

Jun 2

Drifting Preference Optimization for One-Step Generative Models

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

diffusion fine-tuning benchmarks safety

arXiv Machine Learning

Aug 26

Scaling Reinforcement Learning for Diffusion Models via Velocity Matching

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

llms diffusion reinforcement-learning fine-tuning

arXiv AI

Jun 16

TuneJury: An Open Metric for Improving Music Generation Preference Alignment

arXiv:2606. 17006v1 Announce Type: cross Abstract: We introduce TuneJury, an open, instance-level pairwise reward model for text-to-music that predicts a music preference score from a text prompt and an audio clip.

By Yonghyun Kim, Junwon Lee, Haiwen Xia, Yinghao Ma, Junghyun Koo, Koichi Saito, Yuki Mitsufuji, Chris Donahue

reinforcement-learning benchmarks safety

One email a morning, machine-written

Related stories

Latent Reward Registers for Diffusion Preference Alignment

How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance

Aligning One-Step Generative Models with Reward-Weighted Transport Distillation

Drifting Preference Optimization for One-Step Generative Models

Scaling Reinforcement Learning for Diffusion Models via Velocity Matching

TuneJury: An Open Metric for Improving Music Generation Preference Alignment