← Search

Qianxun Xu

2 accepted papers

2026

SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls

CVPR 2026

Recent advances in text-to-video diffusion models have enabled high-fidelity and temporally coherent video synthesis. However, current models are predominantly optimized for single-event generation. When handling multi-event prompts, without explicit temporal grounding, such models often produce ble

Cited by 0SourcecodeScholar