15 papers
TinyHistory: Lightweight Video History Embeddings via Two-Stage Context Learning
Lvmin Zhang, Shengqu Cai, Muyang Li +6
History context is central to autoregressive video generation, driving consistency and storytelling for both commercial models and personal use cases. For example, personal users,…
Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis
Zhengfei Kuang, Adam Sun, Liyuan Zhu +7
Modern vehicle platforms are equipped with a rich sensor suite, including LiDAR, calibrated multi-camera rigs, and accurate ego-motion, that in principle offers strong signal for r…
GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation
Jan Ackermann, Shengqu Cai, Boyang Deng +3
Generating geometrically consistent videos remains an open challenge: text-to-video diffusion models trained on web-scale data treat geometry only implicitly, leading to object def…
Mode Seeking meets Mean Seeking for Fast Long Video Generation
Shengqu Cai, Weili Nie, Chao Liu +8
Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to…
Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control
Linxi Xie, Lisong C. Sun, Ashley Neall +3
Extended reality (XR) demands generative models that respond to users' tracked real-world motion, yet current video world models accept only coarse control signals such as text or…
Mixture of Contexts for Long Video Generation
Shengqu Cai, Ceyuan Yang, Lvmin Zhang +10
Long video generation is fundamentally a long context memory problem: models must retain and retrieve salient events across a long range without collapsing or drifting. However, sc…