dev

The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL

📄 Paper Trending (17⬆️): Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering properties such as visual realism and coherent object structure that matching-based training is intended to learn from the data i...

Fuente: HuggingFace_Papers