4 citations · 11 across the 6 of their papers we have counts for
6 papers
RIVA: Leveraging LLM Agents for Reliable Configuration Drift Detection
Sami Abuzakuk, Lucas Crijns, Anne-Marie Kermarrec +2
Infrastructure as code (IaC) tools automate cloud provisioning but verifying that deployed systems remain consistent with the IaC specifications remains challenging. Such configura…
Leveraging Approximate Caching for Faster Retrieval-Augmented Generation
Shai Bergman, Anne-Marie Kermarrec, Diana Petrescu +4
Retrieval-augmented generation (RAG) improves the reliability of large language model (LLM) answers by integrating external knowledge. However, RAG increases the end-to-end inferen…
Boosting Asynchronous Decentralized Learning with Model Fragmentation
Sayan Biswas, Anne-Marie Kermarrec, Alexis Marouani +3
Decentralized learning (DL) is an emerging technique that allows nodes on the web to collaboratively train machine learning models without sharing raw data. Dealing with stragglers…
Harnessing Increased Client Participation with Cohort-Parallel Federated Learning
Akash Dhasade, Anne-Marie Kermarrec, Tuan-Anh Nguyen +2
Federated learning (FL) is a machine learning approach where nodes collaboratively train a global model. As more nodes participate in a round of FL, the effectiveness of individual…
QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation
Akash Dhasade, Yaohong Ding, Song Guo +3
Federated Unlearning (FU) aims to delete specific training data from an ML model trained using Federated Learning (FL). We introduce QuickDrop, an efficient and original FU method…
XChange: A Blockchain-based Mechanism for Generic Asset Trading In Resource-constrained Environments
Martijn de Vos, Can Umut Ileri, Johan Pouwelse
An increasing number of industries rely on Internet-of-Things devices to track physical resources. Blockchain technology provides primitives to represent these resources as digital…