Chuiyang Meng.

RESEARCH

Publications

Papers and manuscripts on mechanistic interpretability, distributed intelligence, and wireless systems.

2026

Social Circuits behind Multi-agent Echo Chambers

Chuiyang Meng, Wenlu Yu, Ming Tang, Cheng Li

arXiv · 2026 Submitted to ICLR 2027

Receiver-state interventions trace how messages correct errors or reinforce them, guiding selective communication between agents.

PDF arXiv
BibTeX 
@misc{meng2026socialcircuits,
  title = {{Social Circuits behind Multi-agent Echo Chambers}},
  author = {Chuiyang Meng and Wenlu Yu and Ming Tang and Cheng Li},
  year = {2026},
  note = {Submitted to ICLR 2027},
  url = {https://arxiv.org/abs/2609.34444},
  eprint = {2609.34444},
  archivePrefix = {arXiv}
}
Figure 1 · Error correction and echo chambers View figure

CORTEX: Learning to Share and Specialize in Dense Language Models

Chuiyang Meng, Ming Tang, Vincent W.S. Wong

arXiv · 2026 Submitted to ICLR 2027

Domain-conditioned learning dynamics shape shared and specialized functions within a single dense language model.

PDF arXiv
BibTeX 
@misc{meng2026cortex,
  title = {{CORTEX: Learning to Share and Specialize in Dense Language Models}},
  author = {Chuiyang Meng and Ming Tang and Vincent W.S. Wong},
  year = {2026},
  note = {Submitted to ICLR 2027},
  url = {https://arxiv.org/abs/2609.34449},
  eprint = {2609.34449},
  archivePrefix = {arXiv}
}
Figure 1(b) · Learning shared and specialized functions with CORTEX View figure

FLoRG: Federated Fine-tuning with Low-rank Gram Matrices and Procrustes Alignment

Chuiyang Meng, Ming Tang, Vincent W.S. Wong

ICLR · 2026 Acceptance rate: 27%

Gram-matrix aggregation and Procrustes alignment make federated fine-tuning more consistent and communication-efficient.

PDF arXiv
BibTeX 
@inproceedings{meng2026florg,
  title = {{FLoRG: Federated Fine-tuning with Low-rank Gram Matrices and Procrustes Alignment}},
  author = {Chuiyang Meng and Ming Tang and Vincent W.S. Wong},
  year = {2026},
  booktitle = {International Conference on Learning Representations (ICLR)},
  url = {https://arxiv.org/abs/2602.17095}
}
Figure 1 · The FLoRG framework View figure

ZorBA: Zeroth-order Federated Fine-tuning of LLMs with Heterogeneous Block Activation

Chuiyang Meng, Ming Tang, Vincent W.S. Wong

IEEE INFOCOM · 2026 Acceptance rate: 18%

Selective transformer-block activation reduces memory use in gradient-free federated fine-tuning.

PDF arXiv
BibTeX 
@inproceedings{meng2026zorba,
  title = {{ZorBA: Zeroth-order Federated Fine-tuning of LLMs with Heterogeneous Block Activation}},
  author = {Chuiyang Meng and Ming Tang and Vincent W.S. Wong},
  year = {2026},
  booktitle = {IEEE International Conference on Computer Communications (INFOCOM)},
  url = {https://arxiv.org/abs/2603.04436}
}
Figure 2 · The ZorBA framework View figure

ASFL: An Adaptive Model Splitting and Resource Allocation Framework for Split Federated Learning

Chuiyang Meng, Ming Tang, Vincent W.S. Wong

IEEE TMC · 2026 Vol. 25, no. 10

Adapting where a model is split balances learning progress, training delay, and energy consumption.

PDF arXiv
BibTeX 
@article{meng2026asfl,
  title = {{ASFL: An Adaptive Model Splitting and Resource Allocation Framework for Split Federated Learning}},
  author = {Chuiyang Meng and Ming Tang and Vincent W.S. Wong},
  year = {2026},
  journal = {IEEE Transactions on Mobile Computing (TMC)},
  volume = {25},
  number = {10},
  url = {https://arxiv.org/abs/2603.04437}
}
Figure 1 · Adaptive split federated learning View figure

2025

Tackling Resource Allocation for Decentralized Federated Learning: A GNN-based Approach

Chuiyang Meng, Ming Tang, Mehdi Setayesh, Vincent W.S. Wong

IEEE TMC · 2025 Vol. 24, no. 10

A graph neural network coordinates neighbor selection and resource allocation for decentralized learning.

PDF Publisher
BibTeX 
@article{meng2025gnntmc,
  title = {{Tackling Resource Allocation for Decentralized Federated Learning: A GNN-based Approach}},
  author = {Chuiyang Meng and Ming Tang and Mehdi Setayesh and Vincent W.S. Wong},
  year = {2025},
  journal = {IEEE Transactions on Mobile Computing (TMC)},
  volume = {24},
  number = {10},
  doi = {10.1109/TMC.2025.3562834}
}
Figure 3 · The proposed GNN model for decentralized federated learning View figure

2023

GNN-based Neighbor Selection and Resource Allocation for Decentralized Federated Learning

Chuiyang Meng, Ming Tang, Mehdi Setayesh, Vincent W.S. Wong

IEEE GLOBECOM · 2023

Learning which neighbors to aggregate with, and how to allocate resources, in a changing wireless network.

PDF
BibTeX 
@inproceedings{meng2023gnnglobecom,
  title = {{GNN-based Neighbor Selection and Resource Allocation for Decentralized Federated Learning}},
  author = {Chuiyang Meng and Ming Tang and Mehdi Setayesh and Vincent W.S. Wong},
  year = {2023},
  booktitle = {IEEE Global Communications Conference (GLOBECOM)}
}
Figure 2 · Graph-based neighbor selection and resource allocation View figure

2017

Design, Analysis, and Field Testing of an Innovative Drone-Assisted Zero-Configuration Localization Framework for Wireless Sensor Networks

Zijun Gong, Cheng Li, Fan Jiang, Ruoyu Su, Ramachandran Venkatesan, Chuiyang Meng, Shuai Han, Yan Zhang, Shudong Liu, Kun Hao

IEEE TVT · 2017 Vol. 66, no. 11

Drone-assisted localization for wireless sensor networks without offline channel configuration.

Publisher
BibTeX 
@article{gong2017drone,
  title = {{Design, Analysis, and Field Testing of an Innovative Drone-Assisted Zero-Configuration Localization Framework for Wireless Sensor Networks}},
  author = {Zijun Gong and Cheng Li and Fan Jiang and Ruoyu Su and Ramachandran Venkatesan and Chuiyang Meng and Shuai Han and Yan Zhang and Shudong Liu and Kun Hao},
  year = {2017},
  journal = {IEEE Transactions on Vehicular Technology},
  volume = {66},
  number = {11},
  doi = {10.1109/TVT.2017.2726939}
}

A New Turbo Equalizer Conditioned on Estimated Channel for MIMO MMSE Receiver

Cheng Li, Fan Jiang, Chuiyang Meng, Zijun Gong

IEEE Comms. Lett. · 2017 Vol. 21, no. 4

Turbo equalization that incorporates both channel estimation error and a priori information.

Publisher
BibTeX 
@article{li2017turbo,
  title = {{A New Turbo Equalizer Conditioned on Estimated Channel for MIMO MMSE Receiver}},
  author = {Cheng Li and Fan Jiang and Chuiyang Meng and Zijun Gong},
  year = {2017},
  journal = {IEEE Communications Letters},
  volume = {21},
  number = {4},
  doi = {10.1109/LCOMM.2016.2638823}
}

A Mobile Relay Selection Strategy in Cooperative Spectrum Sharing Framework

Xiao Deng, Xuanli Wu, Chuiyang Meng, Shuai Han, Xiaojie Fang

IEEE ICC · 2017

Relay selection for cooperative spectrum sharing with mobile users.

Publisher
BibTeX 
@inproceedings{deng2017relay,
  title = {{A Mobile Relay Selection Strategy in Cooperative Spectrum Sharing Framework}},
  author = {Xiao Deng and Xuanli Wu and Chuiyang Meng and Shuai Han and Xiaojie Fang},
  year = {2017},
  booktitle = {IEEE International Conference on Communications (ICC)},
  doi = {10.1109/ICC.2017.7996715}
}