paper-with-me

Papers

MoNe: Modular Neural Memory for Efficient Long Context Inference

2026-08-18 · Wonguk Cho, Kyubyung Chae, Tribhuvanesh Orekondy, Sunghyun Park, Hyoungwoo Park, Jeongho Kim, Arash Behboodi, Kyuwoong Hwang, Sungrack Yun arxiv

We present MoNe, a lightweight modular neural memory that attaches to any frozen pretrained Transformer to enable long-context inference without retraining. MoNe reads context in fixed-size segments via test-time learning of fast-weight neural memory networks with layer-localized gradient updates; at inference, the memory generates keys and values from the query tokens alone, with no context tokens re-read. This two-phase design decouples inference cost from context length, achieving $O(N)$ preprocessing and $O(1)$ query cost with peak GPU memory that does not grow with $N$. At 128K tokens, MoNe reduces both compute and peak GPU memory by approximately 80% compared to ICL with only 6.4% parameter overhead. MoNe generalizes to context lengths far beyond the backbone's native window, achieving strong performance on needle-in-a-haystack and word extraction benchmarks from RULER, where ICL degrades sharply.

📄 PDF Abstract BibTeX arXiv:2608.17616

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Self-Supervised Interpretable End-to-End Learning via Latent Functional Modularity

2024-02-21 · Hyunki Seong, David Hyunchul Shim

We introduce MoNet, a novel functionally modular network for self-supervised and interpretable end-to-end learning. By leveraging its functional modularity with a latent-guided contrastive loss function, MoNet efficientl…

Autonomous NavigationDecision MakingExplainable artificial intelligenceSpecificity

InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU

2025-02-13 · Heejun Lee, Geon Park, Jaduk Suh, Sung Ju Hwang

In modern large language models (LLMs), handling very long context lengths presents significant challenges as it causes slower inference speeds and increased memory costs. Additionally, most existing pre-trained LLMs fai…

GPULanguage ModelingLanguage Modelling

Local Pheromone Network: Sparse Local Learning with Multi-Scale Synaptic Trails, Consolidation, and Replay

2026-06-22 · Xingcheng Fu, Xianjun Chen, Zhihao Li arxiv

Backpropagation-trained dense neural networks are powerful function approximators, but they couple learning across many parameters and can overwrite previous associations when tasks conflict. This paper describes Local P…

Understanding LoRA as Knowledge Memory: An Empirical Analysis

2026-03-01 · Seungju Back, Dongwoo Lee, Naun Kang, Taehee Lee 외 arxiv

Continuous knowledge updating for pre-trained large language models (LLMs) is increasingly necessary yet remains challenging. Although inference-time methods like In-Context Learning (ICL) and Retrieval-Augmented Generat…

ContextPilot: Fast Long-Context Inference via Context Reuse

2025-11-05 · Yinsicheng Jiang, Yeqi Huang, Liang Cheng, Cheng Deng 외 arxiv

AI applications increasingly depend on long-context inference, where LLMs consume substantial context to support stronger reasoning. Common examples include retrieval-augmented generation, agent memory layers, and multi-…