Minghui Liwang

TRACER: Adaptive Multi-Robot Social Navigation via Joint Human-Response Prediction and Interaction-Aware Replanning

Multi-robot navigation in human-shared spaces is inherently interactive: coordinated robot motions influence how nearby entities respond, while those responses provide valuable information for subsequent robot decisions. However, existing methods typically address action-conditioned prediction, multi-robot planning, or...

Predictive Rolling-Horizon Optimization for Commitment-Aware Model-Parallel Inference under Spatio-Temporal Edge Dynamics

Model-parallel inference over dynamic edge systems requires scheduling decisions that account for not only instantaneous resources but also future resource contention and reliable service commitments. Existing edge-inference designs, however, predominantly optimize performance metrics based on current or short-term sys...

Convergence of Practical Muon

Muon is emerging as a promising alternative to AdamW for large-scale neural network training, yet theoretical understanding of its practical implementation remains incomplete, as existing analyses often simplify or omit two key components: (i) practical Newton--Schulz iterations with empirically tuned polynomial coeffi...

AsyncFed-SAR: Toward Communication-Efficient Asynchronous Federated Learning for SAR Image Target Recognition

HermesHFL: Incentive-Compatible Hierarchical Federated Unlearning for Dynamic LLM Fine-Tuning

Her HermesHFL, a hierarchical federated learning framework that supports selective unlearning, dynamic client participation, and client reintegration for scalable LLM fine-tuning via parameter-efficient fine-tuning (PEFT) with LoRA, is proposed and developed.

Federated Foundation Models over Vehicular Networks

The promise of M3T FedFMs for vehicular networks is demonstrated and the implementation of the fundamental training/fine-tuning principles of M3T FedFMs are introduced to facilitate reproducibility and stimulate research in this emerging area.

An Option-Based Hierarchical Approach for Dynamic Mobile Crowdsensing Over Edge-Assisted UAV Networks

With the rapid advancement of edge computing and uncrewed aerial vehicle (UAV) technologies, edge-assisted UAV networks have emerged as a promising solution for efficient data collection in mobile crowdsensing (MCS). This paper addresses the problem of decentralized dynamic data collection in UAV networks supported by...

Flying over The Uncertain Nature (FORTUNE): Intelligent and Humanistic 3D Path Planning for Low-Altitude Collaboration

This paper studies 3D multi-UAV path planning and task assignment under uncertain ground PoI demands, and proposes FORTUNE, a hierarchical offline-online framework that consistently outperforms state-of-the-art methods in effectiveness, scalability, and practical applicability.

CRAM: Cooperative Resource Allocation With Spotlighting for Zero-Interruption ISAC Networks

The emergence of sixth-generation (6G) communication systems promotes an integrated sensing and communications (ISAC) framework to address growing demands for seamless connectivity. This paper proposes a cooperative resource allocation method (CRAM) that enables uninterrupted service for mobile terminals (MTs) moving a...

Toward 6G Edge Intelligence: Lightweight LLMs for Intent-Driven Network Automation

Future 6G networks are envisaged to tightly integrate communication, sensing, and computing, demanding real-time, intent-driven intelligence at the edge. While large language models (LLMs) excel in intent recognition and semantic reasoning, their application to real-time network lifecycle management at the edge is limi...