10 papers
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
Runhui Huang, Qihui Zhang, Zhe Liu +3
The paper introduces SpectraReward, a training-free method that uses pretrained multimodal large language models to score generated images by measuring how well the original text p…
Leveraging Verifier-Based Reinforcement Learning in Image Editing
Hanzhong Guo, Jie Wu, Jie Liu +6
While Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm for text-to-image generation, its application to image editing remains largely unexplored. A k…
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
Runhui Huang, Jie Wu, Rui Yang +2
In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal…
LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
Zhanhao Liang, Tao Yang, Jie Wu +2
This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differen…
OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization
Jiacheng Zhang, Jie Wu, Weifeng Chen +4
Video diffusion models (VDMs) have demonstrated remarkable capabilities in text-to-video (T2V) generation. Despite their success, VDMs still suffer from degraded image quality and…
DanceGRPO: Unleashing GRPO on Visual Generation
Zeyue Xue, Jie Wu, Yu Gao +8
Recent advances in generative AI have revolutionized visual content creation, yet aligning model outputs with human preferences remains a critical challenge. While Reinforcement Le…