Cross-Model Memory Transfer via Target-Side Reader Adaptation
Summary
This paper investigates cross-model memory transfer, demonstrating that target-side reader adaptation is crucial for utilizing frozen memory tables across different large language models. It introduces methods for reusable knowledge artifacts with optional adaptation to improve alignment.
View Cached Full Text
Cached at: 08/19/26, 07:56 AM
Paper page - Cross-Model Memory Transfer via Target-Side Reader Adaptation
Source: https://huggingface.co/papers/2608.17050
Abstract
Cross-model reuse of frozen external memory tables depends primarily on aligning a lightweight target-side reader rather than the memory content alone, enabling reusable knowledge artifacts with optional adaptation.
Methods for improving knowledge use in large language models typically fall into two regimes. Non-parametric retrieval offers flexible access to external knowledge, but adds retrieval latency, context overhead, and only shallow integration with the backbone. Parametric adaptation is efficient at inference time, but entangles knowledge with model weights and can be hard to update, audit, or transfer.Engram-stylehashed memoryoccupies a middle regime: it stores learned information in an external, addressable table, yet consumes that table through a small learned reader. This raises a basic question: when such a memory is moved across backbones, what matters more, the frozen memory itself or the target-side reader? We study this question throughcross-model frozen-memory extraction, in which a memory trained on a source model is frozen and attached to a different target model, with only a lightweight reader trained. Ablations show that learned memory content and correct addressing both matter, but the transferred table becomes useful only through a reader aligned to the target model. In downstream question answering tasks, a dual-layer, four-branch reader nearly closes the gap between same-model and cross-model reuse, achieving an average score of 38.8 under our controlled evaluation protocol. Moreover, when the provider reader is directly compatible with the target interface, the frozen artifact can provide substantial utility without target-side training, while optional reader adaptation yields further improvement. These results suggest thatEngramcan serve as a reusable external knowledge artifact, provided that the target has access to a compatible reader interface; target-side adaptation can further improve alignment when direct reader reuse is insufficient.
View arXiv pageView PDFProject pageGitHubAdd to collection
Get this paper in your agent:
hf papers read 2608\.17050
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.17050 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.17050 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.17050 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
$\varepsilon$-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution
The paper introduces ε-MemEvo, a framework for cross-task knowledge transfer in LLM-based program evolution, storing tactic memories as natural-language summaries and using an adaptive injection gate. It reports consistent gains on 8 optimization benchmarks with less than 1% computational overhead.
@vintcessun: A 'knowledge hard drive' that can be plugged across models — the difficulty lies not in moving the memory table, but in configuring the read head for the target model. https://arxiv.org/abs/2608.17050 The paper first trains Engram hash memory with the source model, then freezes the memory and target backbone, only training the reader to complete addressing...
This paper proposes a method for cross-model memory transfer through target-side reader adaptation, using Engram hash memory and a lightweight reader, achieving 38.8 on QA tasks, and applicable to Agent memory updates and audits. The limitation is that it was only tested up to 9B models, with scaling laws unknown.
ComMem: Complementary Memory Systems for Test-Time Adaptation of Vision-Language Models
ComMem proposes complementary memory systems inspired by biological memory to improve test-time adaptation of vision-language models, outperforming state-of-the-art on 15 benchmarks.
Selective State-Space Adaptation and Retrieval for Language Model Reasoning
Proposes MaLoRA and MaRA, two adapter families that introduce selective state-space recurrence for token-level and context-level adaptation in frozen language models, achieving significant gains on multi-hop reasoning benchmarks like MuSiQue and 2WikiMultihopQA.
Understanding Is Done Early: A Depth Division of Labor in Large Language Models and Its Use for Unbounded-Context Memory
This paper introduces CoMem, a method that exploits the depth-wise division of labor in LLMs to cache intermediate residual tensors and recompute only upper layers for retrieval, enabling bounded read compute and memory independent of stored-context length. Evaluated on Qwen3-8B, CoMem achieves strong long-context performance with significant memory savings and prefill speedups.