activity
20172026
most citedMulti-Armed Bandit Based Client Scheduling for Federated Learning

313 citations · 673 across the 65 of their papers we have counts for

collaborators

69 papers

cs.NI2026

Bridging the Cognitive Gap: A Unified Memory Paradigm for 6G Agentic AI-RAN

Xijun Wang, Zhaoyang Liu, Chenyuan Feng +3

As 6G evolves, the radio access network must transcend traditional automation to embrace agentic AI capable of perception, reasoning, and evolution. A fundamental cognitive gap per…

cs.NI2026

Semantics-Aware Communication:A Differentiated Allocation Perspective

Fangming Zhao, Nikolaos Pappas, Howard H. Yang

We study the joint optimization of timeliness and reliability in semantics-aware Wireless Networked Control Systems (WNCS) under computation resource constraints. The sampled data…

cs.NI2026

Probing for Better Age of Information in Energy-Harvesting Random Access Networks

Ziyi Li, Fangming Zhao, Howard H. Yang

In this paper, we investigate the impact of channel probing and reservation on the Age of Information (AoI) in energy-harvesting (EH) random access networks, where each source reli…

cs.DC2026

Federated Inference for Heterogeneous LLM Communication and Collaboration

Zihan Chen, Zeshen Li, Howard H. Yang +2

Given the limited performance and efficiency of on-device Large Language Models (LLMs), the collaborations between multiple LLMs enable desirable performance enhancements, in which…

cs.LG2025

Timely Parameter Updating in Over-the-Air Federated Learning

Jiaqi Zhu, Zhongyuan Zhao, Xiao Li +3

Incorporating over-the-air computations (OAC) into the model training process of federated learning (FL) is an effective approach to alleviating the communication bottleneck in FL…

cs.LG2025

Feature-Based Semantics-Aware Scheduling for Energy-Harvesting Federated Learning

Eunjeong Jeong, Giovanni Perin, Howard H. Yang +1

Federated Learning (FL) on resource-constrained edge devices faces a critical challenge: The computational energy required for training Deep Neural Networks (DNNs) often dominates…