3 papers
cs.CV2026
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…
cs.CV2026
UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
Jie Liu, Zilyu Ye, Linxiao Yuan +8
Unified models capable of interleaved generation have emerged as a promising paradigm, with the community increasingly converging on autoregressive modeling for text and flow match…
cs.CV2025
OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning
Yuan Gong, Xionghui Wang, Jie Wu +3
In this paper, we introduce OneReward, a unified reinforcement learning framework that enhances the model's generative capabilities across multiple tasks under different evaluation…