The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation Paper • 2511.20256 • Published 15 days ago • 26 • 3
The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation Paper • 2511.20256 • Published 15 days ago • 26 • 3
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Paper • 2505.23380 • Published May 29 • 22 • 2