LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation
- Published
- Source
- arXiv
- Paper number
- 300
- Field
- Computer Vision
- arXiv ID
- 2606.02553
Key points
- To make retrieval more discriminative, the authors introduce Window Temporal Delta Loss, which suppresses redundant local similarity and encourages embeddings to capture meaningful temporal change.
- Experiments across several AR backbones and generation lengths show improved long-form video quality and the best average VBench-Long ranking.
- As far as the authors know, LongLive-RAG is the first open-ended AR long-video generation method to formalize its self-generated latent history as content-addressable retrieval memory.
Paper links
External research summaries. These are not HDATF publications or measured product results.