5 papers
GARDO: Reinforcing Diffusion Models without Reward Hacking
Haoran He, Yuxiao Ye, Jie Liu +7
Fine-tuning diffusion models via online reinforcement learning (RL) has shown great potential for enhancing text-to-image alignment. However, since precisely specifying a ground-tr…
GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
Jing Wang, Jiajun Liang, Jie Liu +10
Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. With…
Scaling Image and Video Generation via Test-Time Evolutionary Search
Haoran He, Jiajun Liang, Xintao Wang +4
As the marginal cost of scaling computation (data and parameters) during model pre-training continues to increase substantially, test-time scaling (TTS) has emerged as a promising…
Flow-GRPO: Training Flow Matching Models via Online RL
Jie Liu, Gongye Liu, Jiajun Liang +6
We propose Flow-GRPO, the first method to integrate online policy gradient reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-t…
Improving Video Generation with Human Feedback
Jie Liu, Gongye Liu, Jiajun Liang +14
Video generation has achieved significant advances through rectified flow techniques, but issues like unsmooth motion and misalignment between videos and prompts persist. In this w…