ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization Paper • 2502.04306 • Published Feb 6 • 19
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement Paper • 2410.13828 • Published Oct 17, 2024 • 4
Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow Paper • 2410.07303 • Published Oct 9, 2024 • 18