相关论文: Lightweight User-Personalization Method for Closed…

Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step…

A fundamental challenge to providing edge-AI services is the need for a machine learning (ML) model that achieves personalization (i.e., to individual clients) and generalization (i.e., to unseen data) properties concurrently. Existing…

This study presents Weighted Sampled Split Learning (WSSL), an innovative framework tailored to bolster privacy, robustness, and fairness in distributed machine learning systems. Unlike traditional approaches, WSSL disperses the learning…

Split Computing (SC), where a Deep Neural Network (DNN) is intelligently split with a part of it deployed on an edge device and the rest on a remote server is emerging as a promising approach. It allows the power of DNNs to be leveraged for…

Split learning (SL) enables data privacy preservation by allowing clients to collaboratively train a deep learning model with the server without sharing raw data. However, SL still has limitations such as potential data privacy leakage and…

Large Language Models (LLMs) demonstrate impressive capabilities in natural language understanding and generation, but incur high communication overhead and privacy risks in cloud deployments, while facing compute and memory constraints…

Federated learning (FL) is one of the popular distributed machine learning (ML) solutions but incurs significant communication and computation costs at edge devices. Federated split learning (FSL) can train sub-models in parallel and reduce…

Federated Learning (FL) plays a critical role in distributed systems. In these systems, data privacy and confidentiality hold paramount importance, particularly within edge-based data processing systems such as IoT devices deployed in smart…

Integrating Federated Learning (FL) with self-supervised learning (SSL) enables privacy-preserving fine-tuning for speech tasks. However, federated environments exhibit significant heterogeneity: clients differ in computational capacity,…

Test-time adaptation (TTA) is an effective approach to mitigate performance degradation of trained models when encountering input distribution shifts at test time. However, existing TTA methods often suffer significant performance drops…

Although recent scientific output focuses on multiple shortest-path problem definitions for road networks, none of the existing solutions does efficiently answer all different types of SP queries. This work proposes SALT, a novel framework…

Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the…

Tuning parallel file system in High-Performance Computing (HPC) systems remains challenging due to the complex I/O paths, diverse I/O patterns, and dynamic system conditions. While existing autotuning frameworks have shown promising results…

Adapter-Tuning (AT) method involves freezing a pre-trained model and introducing trainable adapter modules to acquire downstream knowledge, thereby calibrating the model for better adaptation to downstream tasks. This paper proposes a…

Large Language Models (LLMs) increasingly incorporate multilingual capabilities, fueling the demand to transfer them into target language-specific models. However, most approaches, which blend the source model's embedding by replacing the…

Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. Only processed or `smashed' data can be transmitted from the clients to the server during the SL…

Large labeled data sets are one of the essential basics of modern deep learning techniques. Therefore, there is an increasing need for tools that allow to label large amounts of data as intuitively as possible. In this paper, we introduce…

Privacy-preserving machine learning has become a key conundrum for multi-party artificial intelligence. Federated learning (FL) and Split Learning (SL) are two frameworks that enable collaborative learning while keeping the data private (on…

Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e.g., autonomous driving, yet it still remains notoriously labor-intensive. Pretraining-finetuning approach can alleviate the labeling burden by…

Fine-tuning large language models (LLMs) on private, on-device data can empower tailored personalized AI agents. However, fine-tuning LLMs on resource-constrained edge devices faces significant challenges, including excessive computation…