arXiv (All)
open access
GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs
Hybrid language models interleave Gated DeltaNet (GDN) layers, whose recurrent memory has a fixed size, with full-attention layers, whose key-value (KV) cache grows with the context and dominates serving memory. In this paper, we ask whether the recurrent memory already knows what the attention memo
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
- LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization#1142461
- LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization#1122275
- Steering Under Compression: Dose-Response, Capability Cost, and Failure Asymmetry in Quantized LLMs#974048
- Anchors Enhance Controllability and Reasoning of Diffusion Language Models#1325993
- Repetition, Not Length: Isolating the Counting Failure in Neural Text-to-Speech#1132175
Record · ID 1325650
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