VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL Paper • 2505.15791 • Published May 21, 2025 • 6
Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection Paper • 2505.17558 • Published May 23, 2025 • 15
JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models Paper • 2308.04729 • Published Aug 9, 2023 • 33
