Poster Thu, Sep 10, 2026 • 7:30 AM – 9:30 AM PDT ExHall # 127

Anchored Video Generation: Decoupling Scene Construction and Temporal Synthesis in Text-to-Video Diffusion Models

Mariam Hassan ⋅ Bastien van Delft ⋅ Wuyang Li ⋅ Alexandre ALahi

Keywords: Video Understanding, Generation and Multimodal Learning