Poster Thu, Sep 10, 2026 • 7:30 AM – 9:30 AM PDT ExHall # 95

VoCa: Unified Autoregressive Modeling for Talking Audio-Video Generation

Zhuofan Zong ⋅ Jiale Yuan ⋅ Yufei Liu ⋅ Dongzhi Jiang ⋅ Hao Shao ⋅ Zimu Lu ⋅ Ke Wang ⋅ Yunqiao Yang ⋅ Mingjie Zhan ⋅ Hongsheng LI

Keywords: Video Understanding, Generation and Multimodal Learning