Beyond K/V Caches: Cross-Model State Handoff in Hybrid Linear-Attention LLMs
cs.CL
Submitted: 2026-11-05
Updated: 2026-11-05
Comments: 12 pages, 4 figures, 9 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
- CacheLink: Functional KV Transport for Zero-Prefill Cross-Model Context Handoff
- CacheBridge: Efficient Cross-Model KV Transfer for Multi-Model LLM Serving
- Gated Delta Networks: Improving Mamba2 with Delta Rule
- Kimi Linear: An Expressive, Efficient Attention Architecture
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data