Gary Lee

Gary Lee

AI and learning-based methods for complex systems. Background in signal processing for wireless systems. I also build multi-agent tools for coding, knowledge management, and research operations.

Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

State Estimation and Communication Co-Design in IIoT Systems: A Brief Survey

Published in Journal of Communications and Information Networks, 2026

Surveys joint state estimation and communication co-design for IIoT, from stability-theoretic foundations (data-rate theorem, critical loss rate) through layered network co-design to learning-based unified control frameworks, synthesizing how cross-layer optimization outperforms isolated subsystem approaches.

Recommended citation: P. Li, S. Sun, G. C. F. Lee, C. Chen, S. Zhu, X. Guan, and G. P. Fettweis, “State Estimation and Communication Co-Design in IIoT Systems: A Brief Survey,” Journal of Communications and Information Networks, vol. 11, no. 1, pp. 1--21, Mar. 2026. doi: 10.23919/JCIN.2026.11474252

From Freshness to Effectiveness: Goal-Oriented Sampling for Remote Decision Making

Published in IEEE Transactions on Information Theory, 2026

Shows why freshness (AoI) alone can misalign with decision quality and proposes goal-oriented sampling strategies that prioritize effective information for remote decision-making, supported by analysis and simulations demonstrating improved outcomes.

Recommended citation: A. Li, S. Wu, G. C. Lee, and S. Sun, “From freshness to effectiveness: Goal-oriented sampling for remote decision making,” IEEE Transactions on Information Theory, 2026

MARHO: Hybrid Task Offloading in Maritime MEC via Multi-Agent Reinforcement Learning

Published in IEEE Open Journal of the Communications Society, 2025

Introduces MARHO, a multi-agent reinforcement learning approach for hybrid task offloading in maritime MEC architectures, coordinating agents to reduce average latency and improve service performance compared with existing benchmark strategies.

Recommended citation: J. Ning, A. Li, G. C. Lee, S. Sun, and T. Yang, “MARHO: Hybrid task offloading in maritime mec via multi-agent reinforcement learning,” IEEE Open Journal of the Communications Society, vol. 6, pp. 10 322–10 337, 2025.

Subarea Collaborative Deep Q-Network With Online Learning: Advanced Multi-Agent Routing Strategies for Dynamic Maritime Networks

Published in IEEE Open Journal of the Communications Society, 2025

Proposes Subarea-CDQN, a collaborative deep Q-network with online learning for routing in dynamic maritime networks, partitioning the environment into subareas to improve coordination and robustness under constrained, time-varying connectivity.

Recommended citation: X. Sun, T. Yang, C. Han, G. C. Lee, and S. Sun, “Subarea collaborative deep Q-network with online learning: Advanced multi-agent routing strategies for dynamic maritime networks,” IEEE Open Journal of the Communications Society, 2025.

Unified Upper Bounds on the ML decoding Error Probability of Spinal Codes over Fading Channels

Published in IEEE Transactions on Wireless Communications, 2025

Derives unified upper bounds on maximum-likelihood decoding error probability for spinal codes over fading channels, offering tighter, more interpretable performance guarantees and validating the bounds and insights through numerical results.

Recommended citation: A. Li, X. Chen, S. Wu, G. C. Lee, and S. Sun, “Unified upper bounds on the ML decoding error probability of spinal codes over fading channels,” IEEE Transactions on Wireless Communications, 2025.

RF Challenge: The Data-Driven Radio Frequency Signal Separation Challenge

Published in IEEE Open Journal of the Communications Society, 2025

Presents the Data-Driven RF Signal Separation Challenge as a benchmark for interference rejection, detailing the dataset, evaluation protocol, and baseline solutions to enable comparable, repeatable progress in learning-based RF separation research.

Recommended citation: A. Lancho, A. Weiss, G. C. Lee, T. Jayashankar, B. G. Kurien, Y. Polyanskiy, and G. W. Wornell, “RF challenge: The data-driven radio frequency signal separation challenge,” IEEE Open Journal of the Communications Society, 2025.

Lyapunov-guided Deep Reinforcement Learning for Semantic-aware AoI Minimization in UAV-assisted Wireless Networks

Published in IEEE Transactions on Wireless Communications, 2025

Combines Lyapunov optimization with deep reinforcement learning to control semantic extraction and transmission in UAV-assisted networks, minimizing semantic-aware AoI and improving information recovery quality and timeliness relative to existing approaches.

Recommended citation: Y. Long, S. Gong, S. Sun, G. C. Lee, L. Li, and D. Niyato, “Lyapunov-guided deep reinforcement learning for semantic-aware AOI minimization in UAV-assisted wireless networks,” IEEE Transactions on Wireless Communications, 2025.

Miniaturized electrophoresis electrochemical protein sensor (MEEPS) for multiplexed protein detections

Published in Sensors and Actuators B: Chemical, 2017

Demonstrates the MEEPS platform, a miniaturized electrophoresis–electrochemical sensor that enables multiplexed protein detection from microliter-scale samples, with validated detection of multiple cytokines (e.g., IL-6, IFN-γ, TNF-α, IL-8) from ~10 µL.

Recommended citation: P. Kongsuphol, G. C. Lee, S. K. Arya, S. Y. Chiam, and M. K. Park, “Miniaturized electrophoresis electrochemical protein sensor (MEEPS) for multiplexed protein detections,” Sensors and Actuators B: Chemical, vol. 244, pp. 823–830, 2017.

Fabrication of healthy and disease-mimicking retinal phantoms with tapered foveal pits for optical coherence tomography

Published in Journal of Biomedical Optics, 2015

Develops OCT retinal phantoms that replicate both healthy and disease-like morphology, including tapered foveal pits, to support repeatable system testing and more meaningful benchmarking of retinal segmentation and measurement pipelines.

Recommended citation: G. C. Lee, G. T. Smith, M. Agrawal, T. Leng, and A. K. Ellerbee, “Fabrication of healthy and disease-mimicking retinal phantoms with tapered foveal pits for optical coherence tomography,” Journal of biomedical optics, vol. 20, no. 8, p. 085004, 2015.

Single-shot speckle noise reduction by interleaved optical coherence tomography

Published in Journal of Biomedical Optics, 2014

Introduces interleaved OCT acquisition to decorrelate and average speckle in a single shot, achieving measurable speckle-noise reduction without sacrificing imaging speed, and validates the approach on phantoms and biological tissue.

Recommended citation: L. Duan, H. Y. Lee, G. Lee, M. Agrawal, G. T. Smith, and A. K. Ellerbee, “Single-shot speckle noise reduction by interleaved optical coherence tomography,” Journal of Biomedical Optics, vol. 19, no. 12, p. 120501, 2014.

Effect of polarization on a solid immersion lens of arbitrary thickness

Published in Journal of the Optical Society of America A, 2011

Derives image-space field expressions for solid immersion lenses of arbitrary thickness and analyzes how illumination polarization changes aberrations and focal behavior, identifying conditions (e.g., radial polarization) that improve aplanatic imaging performance.

Recommended citation: K. M. Lim, G. C. Lee, C. J. Sheppard, J. C. Phang, C. L. Wong, and X. Chen, “Effect of polarization on a solid immersion lens of arbitrary thickness,” Journal of the Optical Society of America A, vol. 28, no. 5, pp. 903–911, 2011.

Conference Papers

Advancing AI Challenges for the United States Department of the Air Force

Published in 2025 IEEE High Performance Extreme Computing Conference (HPEC), 2025

Summarizes the DAF–MIT AI Accelerator’s approach to advancing Air Force AI challenges, highlighting problem selection, collaboration mechanisms, and outcomes that translate research into deployable capabilities across defense and civilian applications.

Recommended citation: C. Prothmann, V. Gadepally, J. Kepner, K. Borchard, L. Carlone, Z. Folcik, J. D. Griffith, M. Houle, J. P. How, N. Hughes et al., “Advancing AI challenges for the United States department of the Air Force,” in 2025 IEEE High Performance Extreme Computing Conference (HPEC). IEEE, 2025, pp. 1–8.

An Efficient and Privacy-Enhanced U-Shaped Split Federated Learning Method for Distributed Multi-Client Systems

Published in 2025 IEEE International Conference on Communications Workshops (ICC Workshops), 2025

Introduces a U-shaped split federated learning method that improves privacy by limiting raw data exposure while reducing client/server computation and communication overhead, providing an efficient distributed learning protocol for multi-client deployments.

Recommended citation: X. Sun, T. Yang, C. Han, G. C. Lee, and S. Sun, “An efficient and privacy-enhanced U-shaped split federated learning method for distributed multi-client systems,” in 2025 IEEE International Conference on Communications Workshops (ICC Workshops). IEEE, 2025, pp. 1432–1437.

EdgePrompt: A distributed key-value inference framework for LLMs in 6G networks

Published in IEEE INFOCOM 2025-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2025

Proposes EdgePrompt, a distributed key–value inference framework for deploying LLMs over 6G edge networks, improving scalability and latency for long-context inference by coordinating caching and computation across multiple network nodes.

Recommended citation: J. Ning, P. Zhu, C. Zheng, G. Lee, S. Sun, and T. Yang, “EdgePrompt: A distributed key-value inference framework for LLMs in 6G networks,” in IEEE INFOCOM 2025-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). IEEE, 2025, pp. 1–6.

Testbedding of AI-Powered Resilient Dual-Wireless Network Solutions for Virtual Power Plant

Published in 2025 IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS), 2025

Builds and evaluates a testbed for resilient dual-wireless networking in virtual power plants, integrating AI-driven redundancy management to maintain reliable communication under failures and demonstrating practical feasibility for wireless-enabled VPPs.

Recommended citation: A. Boonkajay, C.-L. Chung, J. Huang, G. Lee, Q. Zhang, C. M. Pang, V. Sridharan, E. Kurniawan, and S. Sun, “Testbedding of AI-powered resilient dual-wireless network solutions for virtual power plant,” in 2025 IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS). IEEE, 2025, pp. 1–5.

Specializing language models for 3GPP standards: Enhancements for technical document queries

Published in 2024 IEEE Globecom Workshops (GC Wkshps), 2025

Enhances open-source language models for querying 3GPP standards by combining domain specialization with retrieval and prompting strategies, improving technical question answering over long, structured documents and demonstrating value in telecom benchmark settings.

Recommended citation: G. C. Lee, D. Khu, F. Guretno, and E. Kurniawan, “Specializing language models for 3GPP standards: Enhancements for technical document queries,” in 2024 IEEE Globecom Workshops (GC Wkshps). IEEE, 2024, pp. 1–6.

High-Reliability Wireless Communications for Virtual Power Plant with Efficient Network Redundancy

Published in 2024 IEEE Globecom Workshops (GC Wkshps), 2025

Introduces a high-reliability wireless architecture for virtual power plants using pre-emptive, on-demand redundancy and efficient retransmission policies, achieving resilient VPP communications while substantially reducing transmission and infrastructure costs.

Recommended citation: J. Huang, G. C. Lee, E. Kurniawan, A. Boonkajay, and S. Sun, “High-reliability wireless communications for virtual power plant with efficient network redundancy,” in 2024 IEEE Globecom Workshops (GC Wkshps). IEEE, 2024, pp. 1–6.

Semantic Pre-Extraction for Energy-Efficient AoI Minimization in UAV-Assisted Wireless Networks

Published in 2025 IEEE Wireless Communications and Networking Conference (WCNC), 2025

Studies UAV-assisted data collection with semantic pre-extraction to reduce payload size and energy use, optimizing age-of-information while preserving task-relevant content and demonstrating improved responsiveness and longer ground-user lifetimes versus baselines.

Recommended citation: Y. Long, G. C. Lee, L. Li, S. Gong, S. Sun, and D. Niyato, “Semantic pre-extraction for energy-efficient AOI minimization in UAV-assisted wireless networks,” in 2025 IEEE Wireless Communications and Networking Conference (WCNC). IEEE, 2025, pp. 1–6.

Sampling to achieve the goal: An age-aware remote markov decision process

Published in 2024 IEEE Information Theory Workshop (ITW), 2024

Formulates an age-aware remote Markov decision process where sampling decisions drive remote control/decision quality, extending AoI-centric models by incorporating goal-oriented costs and side information to derive sampling policies that better support actions.

Recommended citation: A. Li, S. Wu, G. C. Lee, X. Chen, and S. Sun, “Sampling to achieve the goal: An age-aware remote Markov decision process,” in 2024 IEEE Information Theory Workshop (ITW). IEEE, 2024, pp. 121–126.

Odometry-Aided mmWave Communications Using Overparameterized Beamforming Optimization

Published in 2024 IEEE 99th Vehicular Technology Conference (VTC2024-Spring), 2024

Proposes odometry-aided mmWave V2I communications that leverages vehicle motion estimates and an overparameterized beamforming optimization to mitigate position uncertainty, improving beam alignment and link reliability for mobile platforms.

Recommended citation: G. C. Lee, E. Kurniawan, and Y. Zheng, “Odometry-aided mmWave communications using overparameterized beamforming optimization,” in 2024 IEEE 99th Vehicular Technology Conference (VTC2024-Spring). IEEE, 2024, pp. 1–6.

The data-driven radio frequency signal separation challenge

Published in 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), 2024

Defines the data-driven RF signal separation challenge, releasing datasets, tasks, metrics, and baseline results to standardize evaluation and accelerate research on learning-based RF modeling and interference cancellation.

Recommended citation: T. Jayashankar, B. Kurien, A. Lancho, G. C. Lee, Y. Polyanskiy, A. Weiss, and G. W. Wornell, “The data-driven radio frequency signal separation challenge,” in 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW). IEEE, 2024, pp. 53–54.

Score-based source separation with applications to digital communication signals

Published in Advances in Neural Information Processing Systems, 2023

Introduces a score-based (generative) framework for separating superimposed sources, applying it to digital communication signals to improve interference rejection and separation fidelity over prior methods, with reproducible resources provided via a project page.

Recommended citation: T. Jayashankar, G. C. Lee, A. Lancho, A. Weiss, Y. Polyanskiy, and G. Wornell, “Score-based source separation with applications to digital communication signals,” Advances in Neural Information Processing Systems, vol. 36, pp. 5092–5125, 2023.

On Neural Architectures for Deep Learning-Based Source Separation of Co-Channel OFDM Signals

Published in ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023

Evaluates and refines neural architectures for separating co-channel OFDM signals from a single channel, identifying design choices that markedly improve separation and reporting architectures that deliver roughly 30 dB performance gains in studied settings.

Recommended citation: G. C. Lee, A. Weiss, A. Lancho, Y. Polyanskiy, and G. W. Wornell, “On neural architectures for deep learning-based source separation of co-channel OFDM signals,” in ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023, pp. 1–5.

Data-Driven Blind Synchronization and Interference Rejection for Digital Communication Signals

Published in GLOBECOM 2022-2022 IEEE Global Communications Conference, 2023

Develops deep learning methods for blind synchronization and interference rejection directly from received communication signals, showing how data-driven models can jointly handle timing/phase impairments and interference to outperform traditional pipelines.

Recommended citation: A. Lancho, A. Weiss, G. C. Lee, J. Tang, Y. Bu, Y. Polyanskiy, and G. W. Wornell, “Data-driven blind synchronization and interference rejection for digital communication signals,” in GLOBECOM 2022-2022 IEEE Global Communications Conference. IEEE, 2022, pp. 2296–2302.

Exploiting Temporal Structures of Cyclostationary Signals for Data-Driven Single-Channel Source Separation

Published in 2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP), 2022

Exploits cyclostationary temporal structure to enable data-driven single-channel source separation, improving separation quality while reducing computational burden compared with generic deep models by embedding signal-specific temporal cues.

Recommended citation: G. C. Lee, A. Weiss, A. Lancho, J. Tang, Y. Bu, Y. Polyanskiy, and G. W. Wornell, “Exploiting temporal structures of cyclostationary signals for data-driven single-channel source separation,” in 2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2022, pp. 1–6.

Robust Direction of Arrival Estimation in the Presence of Array Faults using Snapshot Diversity

Published in 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2020

Proposes a snapshot-diversity approach for direction-of-arrival estimation that remains accurate under array element faults, jointly estimating DOAs while detecting and localizing faulty sensors to maintain performance with imperfect hardware.

Recommended citation: G. C. Lee, A. S. Rawat, and G. W. Wornell, “Robust direction of arrival estimation in the presence of array faults using snapshot diversity,” in 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP). IEEE, 2019, pp. 1–5.

Use of wavelet transform coefficients for spike detection for a Robust Intracortical Brain Machine Interface

Published in 2017 8th International IEEE/EMBS Conference on Neural Engineering (NER), 2017

Uses wavelet-transform coefficients as discriminative features for neural spike detection in intracortical BMI recordings, improving robustness to signal variability and nonstationarities while offering a practical path to more stable, long-term BMI decoding.

Recommended citation: G. C. Lee, C. Libedinsky, C. Guan, and R. So, “Use of wavelet transform coefficients for spike detection for a robust intracortical brain machine interface,” in 2017 8th International IEEE/EMBS Conference on Neural Engineering (NER). IEEE, 2017, pp. 540–543.

Fabrication of anatomically tapered foveal pits for retinal phantoms for optical coherence tomography

Published in SPIE BiOS Design and Performance Validation of Phantoms Used in Conjunction with Optical Measurement of Tissue VII, 2015

Presents a fabrication method for OCT retinal phantoms with anatomically tapered foveal pits, enabling more realistic system validation and providing ground-truth geometries that support improved evaluation of retinal layer segmentation algorithms.

Recommended citation: G. C. Lee, G. T. Smith, M. Agrawal, and A. K. Ellerbee, “Fabrication of anatomically tapered foveal pits for retinal phantoms for optical coherence tomography,” in Design and Performance Validation of Phantoms Used in Conjunction with Optical Measurement of Tissue VII, vol. 9325. SPIE, 2015, pp. 14–20.