arXiv (All)
open access
Keepsake: Selective Spatial Memory for Long-Horizon Video Generation
Long-horizon camera-controlled video generation relies on persistent memory to maintain scene consistency. Existing systems follow two strategies to achieve this consistency. Full-history approaches retain all generated observations, causing unbounded storage and retrieval costs. Selective-construct
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Memory Forcing: Attendable Mid-Horizon History for Streaming Video Generation#1249036
- Long-horizon Video Generation with Slot Memory Addressed By Region Tokens#1345080
- Does Video Memory Use What It Retrieves? A Causal Audit of Memory Specificity#1000061
- Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution#1131548
- World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models#1342651
Record · ID 1215686
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive