arXiv (All)
open access
Offline Makes Online Better: Calibrated Cache Compression for Video Generation
Token merging is an effective approach to reducing KV-cache memory consumption in autoregressive video generation by clustering temporally redundant tokens and retaining only a small set of representatives. Existing methods, however, typically apply a uniform merging ratio across all attention layer
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
- Recast the Past: Stable Long Video Generation with Full Context Memory#1411961
- FrameFold: Response-Guided KV Cache Consolidation for Autoregressive Long Video Generation#1325464
- DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency#1144063
- Long-horizon Video Generation with Slot Memory Addressed By Region Tokens#1345080
- Cartridges++: KV Cache Compression without Off-Context Derailment#1130275
Record · ID 1412164
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