Mao Weijia PRO

benzweijia's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented 2 papers about 2 months ago

The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation

Paper • 2511.20256 • Published Nov 25, 2025 • 27 •

3

The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation

Paper • 2511.20256 • Published Nov 25, 2025 • 27 •

3

commented a paper 8 months ago

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

Paper • 2505.23380 • Published May 29, 2025 • 22 •

2