Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval
Top Cited Papers
Open Access
- 14 December 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Abstract
No abstract availableAll Related Versions
Funding Information
- National Nature Science Foundation of China (62402406)
This publication has 8 references indexed in Scilit:
- World and Human Action Models towards gameplay ideationNature, 2025
- MotionCtrl: A Unified and Flexible Motion Controller for Video Generation2024
- WonderJourney: Going from Anywhere to Everywhere2024
- T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion ModelsProceedings of the AAAI Conference on Artificial Intelligence, 2024
- Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion2024
- RoFormer: Enhanced transformer with Rotary Position EmbeddingNeurocomputing, 2023
- Adding Conditional Control to Text-to-Image Diffusion Models2023
- Scalable Diffusion Models with Transformers2023