today local_bar

Shengqu Cai

PhD student, Stanford University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models

#3917 Spotlight · Lvmin Zhang, Shengqu Cai, Muyang Li, Gordon Wetzstein, Maneesh Agrawala

Methods for packing frame context and preventing drifting phenomenon in next-frame-prediction video models