Poster Thu, Sep 10, 2026 • 7:30 AM – 9:30 AM PDT ExHall # 142

VC-VAE: Leveraging Video Codecs for Training-Efficient and High-Fidelity Video VAE

Xinxu Ge ⋅ Shang Chai ⋅ Litong Gong ⋅ Zitong Yu ⋅ Xin Liu ⋅ Tiezheng Ge

Keywords: Video Understanding, Generation and Multimodal Learning