arXiv (All)
open access
PREM: Prefix-Steered Recurrent Memory for Long-Video Understanding
Long-video understanding must capture transient visual evidence under strict token budgets, yet existing methods compress frames, append memory tokens, or alter internal key-value (KV) caches. We introduce Prefix-Steered Recurrent Memory (PREM), a memory-token-free framework for frozen vision-langua
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
- Does Video Memory Use What It Retrieves? A Causal Audit of Memory Specificity#1000061
- LOCI: Spatial Linear Memory for Streaming World Models#1154485
- SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models#972594
- DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming Video#1063681
- DensityKV: Density-Guided KV Cache Compression for Long Video Generation#781200
Record · ID 1049340
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