arXiv:2607. 17572v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences.
By Ruiyi Ding, Jie Li, He Kang, Ziyan Liu, Chengru Song, Yuan chen
arXiv:2607. 17572v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences.
By Ruiyi Ding, Jie Li, He Kang, Ziyan Liu, Chengru Song, Yuan chen
arXiv:2606. 30376v1 Announce Type: new Abstract: Aligning generative flow models on continuous spaces via online reinforcement learning is constrained by intractable trajectory likelihoods.
By Zheming Fu, Ruizhe He, Wei Shang, Xiaoxiao Ma, Lei Wang, Chang Liu, Siming Fu
arXiv:2604. 18194v2 Announce Type: replace Abstract: Single-step generators promise high-fidelity synthesis at a fraction of the inference and training cost of ordinary differential equation (ODE)-based flow models, a central concern when compute is limited.
By Arkadii Kazanskii, Tatiana Petrova, Andrey Ustyuzhanin, Konstantin Bagrianskii, Aleksandr Puzikov, Radu State
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:2606. 08602v1 Announce Type: cross Abstract: We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems.
By Boshu Lei, Kostas Daniilidis, Antonio Loquercio