Yu-Jiang Pu

NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation

Diffusion models have recently advanced text-to-video (T2V) generation, yet they still struggle with fine-grained compositional alignment, such as attribute binding, spatial relations, and object interactions. While reward-based fine-tuning improves alignment, it is susceptible to reward hacking and adapts poorly to ne...