作者位次 #7/9ICML 2026Poster· Deep Learning / Generative Models and Autoencoders
AlignVid: Taming Visual Dominance via Training-Free Attention Modulation in Text-guided Image-to-Video Generation
Yexin Liu · Wenjie Shu · Zile Huang · Haoze Zheng · Yueze Wang · Manyuan Zhang · Jinjing Zhu · Ser-Nam Lim · Harry Yang