paper-with-me

Papers

EdgeRAG: Online-Indexed RAG for Edge Devices

2024-12-30 · Korakit Seemakhupt, Sihang Liu, Samira Khan

Deploying Retrieval Augmented Generation (RAG) on resource-constrained edge devices is challenging due to limited memory and processing power. In this work, we propose EdgeRAG which addresses the memory constraint by pruning embeddings within clusters and generating embeddings on-demand during retrieval. To avoid the latency of generating embeddings for large tail clusters, EdgeRAG pre-computes and stores embeddings for these clusters, while adaptively caching remaining embeddings to minimize redundant computations and further optimize latency. The result from BEIR suite shows that EdgeRAG offers significant latency reduction over the baseline IVF index, but with similar generation quality while allowing all of our evaluated datasets to fit into the memory.

📄 PDF Abstract BibTeX arXiv:2412.21023

Code (0)

등록된 구현이 없습니다.

Tasks

RAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

2026-06-18 · Md Nayem Uddin, Amir Saeidi, Eduardo Blanco, Chitta Baral arxiv

Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of relevant facts, identifiers, constraints, and…

KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities

2025-07-10 · Hruday Markondapatnaikuni, Basem Suleiman, Abdelkarim Erradi, Shijing Chen arxiv

Fine-tuning is an immensely resource-intensive process when retraining Large Language Models (LLMs) to incorporate a larger body of knowledge. Although many fine-tuning techniques have been developed to reduce the time a…

Text SummarizationQuestion AnsweringKnowledge Graphs

Learning Graph-Indexed Trajectory Patterns for Stochastic On-Time Arrival Routing

2025-08-24 · Xing Wei, Yuanhang Wang, Duoxiang Zhao, Zezhou Zhang 외 arxiv

Correlated link travel times create decision-relevant patterns in partial route histories. In stochastic on-time arrival (SOTA) routing, each route prefix forms a variable-length, graph-indexed sequence in which traverse…

Reinforcement LearningDecision Making

Asynchronous Online Federated Learning for Edge Devices with Non-IID Data

2019-11-05 · Yujing Chen, Yue Ning, Martin Slawski, Huzefa Rangwala

Federated learning (FL) is a machine learning paradigm where a shared central model is learned across distributed edge devices while the training data remains on these devices. Federated Averaging (FedAvg) is the leading…

Federated Learning

A Lightweight Digital-Twin-Based Framework for Edge-Assisted Vehicle Tracking and Collision Prediction

2026-03-07 · Murat Arda Onsu, Poonam Lohan, Burak Kantarci, Aisha Syed 외 arxiv

Vehicle tracking, motion estimation, and collision prediction are fundamental components of traffic safety and management in Intelligent Transportation Systems (ITS). Many recent approaches rely on computationally intens…

Trajectory PredictionObject Detection