On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification Paper • 2508.05629 • Published Aug 7, 2025 • 180
Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization Paper • 2504.18397 • Published Apr 25, 2025 • 2
Subject-Consistent and Pose-Diverse Text-to-Image Generation Paper • 2507.08396 • Published Jul 11, 2025 • 15
