14 citations · 20 across the 25 of their papers we have counts for
27 papers
To Defer or Not to Defer? Online Learning with LLMs and Congested Experts
Vasileios Saketos, William Reveillard, Alexandre Proutiere +2
Modern AI systems increasingly combine large language models (LLMs) with human experts, using the LLM to handle routine queries while deferring uncertain cases for expert review. W…
SkillCom: Decomposing LLM-based Semantic Communication into Task and Channel Aware Skills
Jingwen Fu, Ming Xiao, Mikael Skoglund
Large language models (LLMs) are increasingly used as semantic encoders and decoders in semantic communication. However, current LLM based systems mostly remain monolithic: a singl…
DriftDecode: One-Step Wireless Image Decoding via Drifting-Inspired Detail Recovery
Jingwen Fu, Ming Xiao, Mikael Skoglund
Generative receivers for wireless image transmission can improve reconstruction quality, but diffusion-based and flow-based decoding relies on iterative inference and therefore inc…
Channel-coded Over-the-Air Computation
Shudi Weng, Ming Xiao, Mikael Skoglund
AirComp enables efficient wireless data aggregation, however, its computation accuracy is vulnerable to channel impairments. As a promising solution, the role of redundancy for Air…
Perfectly Private Over-the-Air Computation
Shudi Weng, Ming Xiao, Mikael Skoglund
This paper studies a key research question: how to achieve perfect privacy in over-the-air computation (AirComp)? The problem is particularly intriguing due to a dilemma. Real-fiel…
Byzantine-Robust and Communication-Efficient Distributed Training: Compressive and Cyclic Gradient Coding
Chengxi Li, Youssef Allouah, Rachid Guerraoui +2
In this paper, we study the problem of distributed training (DT) under Byzantine attacks with communication constraints. While prior work has developed various robust aggregation r…
Biased Compression in Gradient Coding for Distributed Learning
Chengxi Li, Ming Xiao, Mikael Skoglund
Communication bottlenecks and the presence of stragglers pose significant challenges in distributed learning (DL). To deal with these challenges, recent advances leverage unbiased…
Quantization-Aware Collaborative Inference for Large Embodied AI Models
Zhonghao Lyu, Ming Xiao, Mikael Skoglund +2
Large artificial intelligence models (LAIMs) are increasingly regarded as a core intelligence engine for embodied AI applications. However, the massive parameter scale and computat…
Coding-Enforced Resilient and Secure Aggregation for Hierarchical Federated Learning
Shudi Weng, Ming Xiao, Mikael Skoglund
Hierarchical federated learning (HFL) has emerged as an effective paradigm to enhance link quality between clients and the server. However, ensuring model accuracy while preserving…
On Resilient and Efficient Linear Secure Aggregation in Hierarchical Federated Learning
Shudi Weng, Xiang Zhang, Yizhou Zhao +3
In this paper, we study the fundamental limits of hierarchical secure aggregation under unreliable communication. We consider a hierarchical network where each client connects to m…
Land-then-transport: A Flow Matching-Based Generative Decoder for Wireless Image Transmission
Jingwen Fu, Ming Xiao, Mikael Skoglund +1
Due to strict rate and reliability demands, wireless image transmission remains difficult for both classical layered designs and joint source-channel coding (JSCC), especially unde…
Robust Multi-modal Task-oriented Communications with Redundancy-aware Representations
Jingwen Fu, Ming Xiao, Zhonghao Lyu +2
Semantic communications for multi-modal data can transmit task-relevant information efficiently over noisy and bandwidth-limited channels. However, a key challenge is to simultaneo…
Computation-resource-efficient Task-oriented Communications
Jingwen Fu, Ming Xiao, Chao Ren +1
The rapid development of deep-learning enabled task-oriented communications (TOC) significantly shifts the paradigm of wireless communications. However, the high computation demand…
Cooperative Gradient Coding
Shudi Weng, Ming Xiao, Chao Ren +1
This work studies gradient coding (GC) in the context of distributed training problems with unreliable communication. We propose cooperative GC (CoGC), a novel gradient-sharing-bas…
Coding-Enforced Robust Secure Aggregation for Federated Learning Under Unreliable Communication
Shudi Weng, Chao Ren, Yizhou Zhao +2
This work studies privacy-preserving federated learning (ppFL) under unreliable communication. In ppFL, zero-sum privacy noises enables privacy protection without sacrificing model…
Coded Robust Aggregation for Distributed Learning under Byzantine Attacks
Chengxi Li, Ming Xiao, Mikael Skoglund
In this paper, we investigate the problem of distributed learning (DL) in the presence of Byzantine attacks. For this problem, various robust bounded aggregation (RBA) rules have b…
The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks
Zhonghao Lyu, Ming Xiao, Jie Xu +2
The growing demand for large artificial intelligence model (LAIM) services is driving a paradigm shift from traditional cloud-based inference to edge-based inference for low-latenc…
Heterogeneity-Aware Client Sampling for Optimal and Efficient Federated Learning
Shudi Weng, Chao Ren, Ming Xiao +1
Federated learning (FL) commonly involves clients with diverse communication and computational capabilities. Such heterogeneity can significantly distort the optimization dynamics…
Supplementary File: Coded Cooperative Networks for Semi-Decentralized Federated Learning
Shudi Weng, Ming Xiao, Chao Ren +1
To enhance straggler resilience in federated learning (FL) systems, a semi-decentralized approach has been recently proposed, enabling collaboration between clients. Unlike the exi…
Supplementary File: Cooperative Gradient Coding for Semi-Decentralized Federated Learning
Shudi Weng, Chengxi Li, Ming Xiao +1
Stragglers' effects are known to degrade FL performance. In this paper, we investigate federated learning (FL) over wireless networks in the presence of communication stragglers, w…
Adaptive Coded Federated Learning: Privacy Preservation and Straggler Mitigation
Chengxi Li, Ming Xiao, Mikael Skoglund
In this article, we address the problem of federated learning in the presence of stragglers. For this problem, a coded federated learning framework has been proposed, where the cen…
Fluid Antenna Array Enhanced Over-the-Air Computation
Deyou Zhang, Sicong Ye, Ming Xiao +3
Over-the-air computation (AirComp) has emerged as a promising technology for fast wireless data aggregation by harnessing the superposition property of wireless multiple-access cha…
Beamforming Design for Active RIS-Aided Over-the-Air Computation
Deyou Zhang, Ming Xiao, Mikael Skoglund +1
Over-the-air computation (AirComp) is emerging as a promising technology for wireless data aggregation. However, its performance is hampered by users with poor channel conditions.…
Over-the-Air Computation Empowered Federated Learning: A Joint Uplink-Downlink Design
Deyou Zhang, Ming Xiao, Mikael Skoglund
In this paper, we investigate the communication designs of over-the-air computation (AirComp) empowered federated learning (FL) systems considering uplink model aggregation and dow…