Md Zesun Ahmed Mia

PhD Candidate, Electrical Engineering

Pennsylvania State University

Ex-Micron ML Engineer Intern

Ex-Intel Graduate Technical Intern

About Zesun

“Curiosity drives me to seek new questions and create new knowledge. I believe progress in science comes from collaboration, open-mindedness, and the courage to explore beyond boundaries.”

I am a PhD candidate in Electrical Engineering at Pennsylvania State University, specializing in neuromorphic computing, machine learning hardware, and emerging semiconductor devices. Most recently, I served as a Machine Learning Engineer Intern at Micron Technology (May–July 2026), analyzing NVM-based Compute-in-Memory architectures for LLM inference acceleration. Previously, I was a Graduate Technical Intern at Intel Corporation (May–July 2025), working on thin film process development and device integration for next-generation computing systems.

Research Focus

My research centers on brain-inspired computing architectures and memory-centric machine learning acceleration that bridge the gap between biological neural networks, emerging memory devices, and artificial intelligence hardware. I am particularly interested in:

Neuromorphic Computing & Brain-Inspired AI:

Developing astromorphic transformers that incorporate astrocyte-neuron interactions
Creating bio-inspired machine learning algorithms for efficient long-context processing
Advancing spiking neural networks (SNNs) and algorithm-device co-design

Machine Learning Hardware & AI Accelerators:

Designing in-memory computing architectures for edge AI and hyperscale inference applications
Building DG-FeFET Compute-in-Memory accelerators for dynamic-operand ML workloads, with TrilinearCIM demonstrating runtime-reprogramming-free Transformer attention
Pathfinding CIM-NVM architectures for LLM inference, including energy/latency trade-offs and serving disaggregation (Prefill–Decode, Attention–FFN)
Optimizing ML accelerator designs for neuromorphic and Transformer workloads
Developing energy-efficient AI hardware solutions

Emerging Devices & Semiconductor Technology:

Investigating ferroelectric devices (FeFET) for neuromorphic applications
Researching spintronics and non-volatile memory (NVM) technologies
Advancing device-circuit co-design methodologies

Academic Background

I am currently pursuing a Doctor of Philosophy (PhD) in Electrical Engineering at Pennsylvania State University, focusing on neuromorphic computing and brain-inspired AI hardware. My doctoral research centers on developing novel astromorphic computing architectures that integrate astrocyte-neuron interactions to enhance machine learning efficiency and long-context processing capabilities.

I completed my Master of Science in Electrical Engineering at Penn State with a perfect 4.00 GPA, specializing in neuromorphic computing for lifelong learning. My graduate coursework and research provided deep expertise in device-circuit co-design, machine learning hardware, and emerging semiconductor technologies.

My undergraduate degree in Electrical and Electronic Engineering from Bangladesh University of Engineering and Technology (BUET) provided a strong foundation in semiconductor device physics, circuit design, and electronics fundamentals. This rigorous program established my core knowledge in electrical engineering principles and prepared me for advanced graduate research.

Industry Experience

As a Machine Learning Engineer Intern at Micron Technology (05/2026–07/2026) in the Pathfinding and Strategy Group (Richardson, TX), I analyzed NVM-based Compute-in-Memory (CIM) architectures for LLM inference acceleration. I modeled technology-agnostic NVM device characteristics, characterized LLM serving under Prefill–Decode and Attention–FFN disaggregation (TPOT/TTFT), and investigated quantization error and CIM analog error mitigation for memory-centric ML inference.

As a Graduate Technical Intern at Intel Corporation (05/2025–07/2025), I worked on thin film deposition process development for advanced technology nodes. I designed and executed Design of Experiments (DOE) for exploratory deposition projects, conducted material characterization (DSIMS, XRR, stress analysis), and developed AI-driven predictive models to assess process impact on circuit electrical parameters and device reliability. This experience bridged my semiconductor process knowledge with ML-based process-circuit co-optimization.

Technical Expertise

ML Systems & Accelerators:

Hardware-aware ML, ML accelerator/ASIC design, neural network accelerator architecture
Transformer/LLM acceleration, model compression (PTQ/QAT, pruning, distillation), mixed-precision (FP16/INT8)
Device-circuit-ML co-design, dataflow optimization, PIM, near-memory computing

Programming & ML Frameworks:

Python, CUDA, C/C++, MATLAB, Verilog, Shell/Bash, Git, Docker
PyTorch, TensorFlow, JAX, ONNX, TensorRT; experiment tracking (W&B, Matplotlib); data tooling (Pandas, NumPy, Jupyter)

Digital/ASIC Design:

RTL design, CMOS/FinFET circuit design, SRAM design, sense amplifier design, memory peripheral circuits
FPGA prototyping, synthesis, P&R, DFT, static timing analysis, timing closure

EDA Tools & Device Simulation:

Cadence Virtuoso, Spectre, HSPICE, TCAD Sentaurus, COMSOL Multiphysics
ModelSim, Quartus, Vivado, Synopsys (Design Compiler, PrimeTime, VCS)
ADC/DAC design, mixed-signal, CIM systems

Device Characterization & Fabrication:

AFM, SEM, TEM, XRD, XRR, Probe station measurements, Hall effect characterization
Lithography: Optical (MLA150) and E-beam (EBPG5200); Etching: Ion beam dry and wet chemical
Deposition: CVD, PVD, sputtering; Magnetic Probe Station (SemiProbe), Keithley/Keysight with LabVIEW

Process Integration & DTCO:

Semiconductor process integration, thin film deposition (CVD, HDP-CVD, PVD), yield optimization
Design-technology co-optimization (DTCO), system-technology co-optimization (STCO), cross-layer PPA

AI & Advanced Computing:

Advanced proficiency in generative AI tools (Cursor, GitHub Copilot, Cline) for research and code development
Prompt engineering, AI-assisted development, edge AI optimization

Research Impact & Publications

My recent work includes TrilinearCIM, a DG-FeFET Compute-in-Memory architecture for memory-centric Transformer acceleration, and RMAAT, an ICLR 2026 bio-inspired long-context Transformer architecture. Industry pathfinding at Micron further shaped how I evaluate CIM-NVM opportunities for LLM inference. As supervisor and corresponding author, I also contributed to an NCE 2026 paper on energy-aware spike budgeting for continual learning in SNNs with ULAB student collaborators. My research has been published in venues including ICLR, Neuromorphic Computing and Engineering (NCE), IEEE Transactions on Cognitive and Developmental Systems, and Matter (Cell Press), spanning astromorphic computing, ML acceleration, neuromorphic devices, and semiconductor technology.

Teaching & Mentorship

As a Graduate Teaching Assistant at Penn State, I mentor students in analog circuit design, Cadence Virtuoso, and semiconductor device physics. Previously, as a Lecturer at ULAB, I supervised undergraduate research that culminated in a peer-reviewed NCE publication—an experience that continues to shape how I approach mentoring. I am passionate about making complex engineering concepts accessible and inspiring the next generation of researchers in neuromorphic computing and ML hardware.

Vision & Future Directions

I envision a future where brain-inspired computing revolutionizes artificial intelligence by creating energy-efficient, adaptive, and fault-tolerant systems. My goal is to develop neuromorphic architectures that not only match but exceed the efficiency of biological neural networks while enabling autonomous learning and real-time adaptation in edge computing environments.

Contact & Academic Identity

📞 Phone: 814-280-7244
📧 Email: zesun.ahmed@psu.edu
🆔 ORCID: 0009-0004-3509-8455
🎓 Google Scholar: View Publications
💼 LinkedIn: Connect with me

Feel free to explore my publications, ongoing projects, and recent news. I welcome opportunities for collaboration and discussion about research in neuromorphic computing, memory-centric ML acceleration, ML hardware, and emerging semiconductor technologies.

Keywords: neuromorphic computing, machine learning hardware, TrilinearCIM, Micron, memory-centric ML acceleration, compute-in-memory, CIM-NVM, LLM inference, spintronics, semiconductor devices, AI accelerators, brain-inspired computing, emerging devices, FeFET, Penn State, electrical engineering, PhD research, Intel Corporation, NCE, edge AI, spiking neural networks, device-circuit co-design

News

Jul 15, 2026	ULAB Student Paper Published in Neuromorphic Computing and Engineering!
Apr 20, 2026	Melvin P. Bloom Memorial Outstanding Doctoral Research Award
Apr 20, 2026	TrilinearCIM Preprint Released on arXiv!
Jan 26, 2026	RMAAT Paper Accepted at ICLR 2026!
Aug 07, 2025	📄 New preprint available! Our paper “Neuromorphic Cybersecurity with Semi-supervised Lifelong Learning” is now on arXiv:2508.04610. This work was presented at ICONS 2025 (July 29-31, 2025) and explores brain-inspired approaches to cybersecurity challenges.

Latest Posts

Aug 01, 2026	Wrapping Up My Micron Internship: CIM-NVM Pathfinding for LLM Inference
Jul 15, 2026	Energy-Aware Spike Budgeting for Continual Learning in SNNs: Our NCE 2026 Paper
Jan 26, 2026	RMAAT Accepted at ICLR 2026: Bringing Astrocyte Biology to Efficient Transformers

Selected Publications

NCE
Energy-aware spike budgeting for continual learning in spiking neural networks for neuromorphic vision

Anika Tabassum Meem, Muntasir Hossain Nadid, and Md Zesun Ahmed Mia

Neuromorphic Computing and Engineering, 2026

Abs DOI arXiv Bib PDF

Neuromorphic vision systems based on spiking neural networks (SNNs) offer event-driven sparse computation for event-based and frame-based cameras, yet catastrophic forgetting remains a critical barrier to deployment in continually evolving environments. Existing continual learning methods, developed primarily for artificial neural networks, seldom jointly optimize accuracy and activity-dependent spike cost, with particularly limited exploration on event-based datasets. We propose an energy-aware spike budgeting framework for continual SNN learning that integrates experience replay, learnable leaky integrate-and-fire neuron parameters, and an adaptive spike-budget controller to enforce dataset-specific spike-activity constraints during training. Our approach exhibits modality-dependent behavior: on frame-based datasets (MNIST, CIFAR-10), spike budgeting acts as a sparsity-inducing regularizer, improving accuracy while reducing spike rates by up to 47%; on event-based datasets (DVS-Gesture, N-MNIST, CIFAR-10-DVS), controlled budget relaxation enables accuracy gains up to 17.45% points with minimal computational overhead. Across five benchmarks spanning both modalities, our method demonstrates consistent performance improvements while keeping spike activity under explicit control, supporting practical continual learning under an activity-driven synaptic-event proxy rather than a direct hardware-energy measurement.
@article{meem2026energy, title = {Energy-aware spike budgeting for continual learning in spiking neural networks for neuromorphic vision}, author = {Meem, Anika Tabassum and Nadid, Muntasir Hossain and Mia, Md Zesun Ahmed}, journal = {Neuromorphic Computing and Engineering}, volume = {6}, number = {3}, pages = {034004}, year = {2026}, publisher = {IOP Publishing}, doi = {10.1088/2634-4386/ae8627}, url = {https://doi.org/10.1088/2634-4386/ae8627}, }
arXiv
Trilinear Compute-in-Memory Architecture for Energy-Efficient Transformer Acceleration

Md Zesun Ahmed Mia, Jiahui Duan, Kai Ni, and 1 more author

arXiv preprint arXiv:2604.07628, 2026

Abs arXiv Bib PDF

Transformer acceleration on Compute-in-Memory (CIM) hardware is bottlenecked by repeated runtime non-volatile memory (NVM) reprogramming of the dynamic attention operands (Q, K, V). We introduce TrilinearCIM, a Double-Gate FeFET (DG-FeFET)-based CIM architecture that performs the full attention dataflow in-memory without runtime ferroelectric reprogramming. A novel three-operand multiply-accumulate primitive (Y = A * B * C), enabled by DG-FeFET back-gate modulation, maps static projection weights to the non-volatile top gate while applying dynamic token activations through the volatile back gate. To our knowledge, this is the first architecture to perform complete Transformer attention computation exclusively in NVM cores without runtime reprogramming. TrilinearCIM reduces global buffer capacity requirements by 3x by eliminating intermediate Q/K matrix storage. Evaluated on BERT-base (GLUE) and ViT-base (ImageNet, CIFAR-10/100), it outperforms conventional FeFET CIM on 7 of 9 GLUE tasks, achieving up to 46.6% energy reduction and 20.4% latency improvement at 37.3% area overhead.
@article{mia2026trilinear, title = {Trilinear Compute-in-Memory Architecture for Energy-Efficient Transformer Acceleration}, author = {Mia, Md Zesun Ahmed and Duan, Jiahui and Ni, Kai and Sengupta, Abhronil}, journal = {arXiv preprint arXiv:2604.07628}, year = {2026}, url = {https://arxiv.org/abs/2604.07628}, }
ICLR
RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers

Md Zesun Ahmed Mia, Malyaban Bal, and Abhronil Sengupta

In International Conference on Learning Representations (ICLR), 2026

Abs arXiv Bib PDF

Astrocytes, an essential component of the brain’s neural circuitry, demonstrate learning capabilities through bioplausible mechanisms such as presynaptic plasticity and hebbian plasticity. However, their integration into computational models remains underexplored. This paper advances astromorphic computing techniques to emulate transformer self-attention mechanisms, leveraging astrocytic nonlinearity and memory retention to improve long-range dependency processing in machine learning and natural language processing (NLP) tasks. Existing transformer models have difficulty handling lengthy contexts with thousands of tokens, even with substantial computational resources. We propose Recurrent Memory Augmented Astromorphic Transformers (RMAAT), integrating astrocytic memory and recurrent processing into self-attention, enabling longer context handling without quadratic complexity growth. Our bioplausible model has been found to outperform traditional transformers in experimental tests conducted on the Long Range Arena benchmark and IMDB dataset. Specifically, our model achieves a significant reduction in memory utilization and computational latency. This paves the way for biologically inspired AI models by illustrating how astrocytic characteristics may enhance the performance and efficiency of computational models.
@inproceedings{mia2026rmaat, title = {{RMAAT}: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers}, author = {Mia, Md Zesun Ahmed and Bal, Malyaban and Sengupta, Abhronil}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026}, url = {https://openreview.net/forum?id=sTkJdbVxsI}, }

ICONS

Neuromorphic Cybersecurity with Semi-Supervised Lifelong Learning

Md Zesun Ahmed Mia, Malyaban Bal, Sen Lu, and 4 more authors

In Proceedings of the International Conference on Neuromorphic Systems (ICONS ’25), 2025

DOI Bib PDF

@inproceedings{mia2025neuromorphic,
  title = {Neuromorphic Cybersecurity with Semi-Supervised Lifelong Learning},
  author = {Mia, Md Zesun Ahmed and Bal, Malyaban and Lu, Sen and Nishibuchi, George M. and Chelian, Suhas and Vasan, Srini and Sengupta, Abhronil},
  booktitle = {Proceedings of the International Conference on Neuromorphic Systems (ICONS '25)},
  pages = {235--238},
  year = {2025},
  publisher = {IEEE Press},
  doi = {10.1109/ICONS69015.2025.00043},
  url = {https://doi.org/10.1109/ICONS69015.2025.00043},
}

IEEE TCDS
Delving deeper into astromorphic transformers

Md Zesun Ahmed Mia, Malyaban Bal, and Abhronil Sengupta

IEEE Transactions on Cognitive and Developmental Systems, 2025

Abs Bib PDF

Preliminary attempts at incorporating the critical role of astrocytes—cells that constitute more than 50% of human brain cells—in brain-inspired neuromorphic computing remain in infancy. This paper seeks to delve deeper into various key aspects of neuron-synapse-astrocyte interactions to mimic self-attention mechanisms in Transformers. The crosslayer perspective explored in this work involves bioplausible modeling of Hebbian and presynaptic plasticities in neuronastrocyte networks, incorporating effects of non-linearities and feedback along with algorithmic formulations to map the neuronastrocyte computations to self-attention mechanism and evaluating the impact of incorporating bio-realistic effects from the machine learning application side. Our analysis on sentiment and image classification tasks (IMDB and CIFAR10 datasets) highlights the advantages of Astromorphic Transformers, offering improved accuracy and learning speed. Furthermore, the model demonstrates strong natural language generation capabilities on the WikiText-2 dataset, achieving better perplexity compared to conventional models, thus showcasing enhanced generalization and stability across diverse machine learning tasks.
@article{mia2025delving, title = {Delving deeper into astromorphic transformers}, author = {Mia, Md Zesun Ahmed and Bal, Malyaban and Sengupta, Abhronil}, journal = {IEEE Transactions on Cognitive and Developmental Systems}, year = {2025}, publisher = {IEEE}, url = {https://ieeexplore.ieee.org/document/10976578/}, }

MWSCAS

Toward Variation-Tolerant Ferroelectric Neural Computing: Special Session Paper

Arnob Saha, Md Zesun Ahmed Mia, Jiahui Duan, and 2 more authors

In 2025 IEEE 68th International Midwest Symposium on Circuits and Systems (MWSCAS), 2025

Bib PDF

@inproceedings{saha2025toward,
  title = {Toward Variation-Tolerant Ferroelectric Neural Computing: Special Session Paper},
  author = {Saha, Arnob and Mia, Md Zesun Ahmed and Duan, Jiahui and Ni, Kai and Sengupta, Abhronil},
  booktitle = {2025 IEEE 68th International Midwest Symposium on Circuits and Systems (MWSCAS)},
  pages = {583--587},
  year = {2025},
  organization = {IEEE},
}

Matter
Self-sensitizable neuromorphic device based on adaptive hydrogen gradient

Tao Zhang, Mingjie Hu, Md Zesun Ahmed Mia, and 8 more authors

Matter, 2024

Abs Bib PDF

Neuromorphic computing aims to achieve superior efficiency by simulating the human brain to surpass traditional computers. It is crucial for neuromorphic devices to possess excellent biological characteristics, offering a vital way to address existing technical bottlenecks in artificial intelligence (AI). Here, we demonstrate adaptive self-sensitization based on a hydrogen gradient in artificial neurons, empowering neural networks to effectively tackle long-standing challenges of model failure in unknown situations beyond pre-defined boundaries. This advancement propels the design of adaptive neuromorphic devices to process unforeseeable signals autonomously. It significantly promotes the development of AI capable of interacting with complex environments, enhancing capabilities to perform tasks such as autonomous navigation, disaster rescue, and outer space exploration and opening up new possibilities for self-guided cognitive systems.
@article{zhang2024self, title = {Self-sensitizable neuromorphic device based on adaptive hydrogen gradient}, author = {Zhang, Tao and Hu, Mingjie and Mia, Md Zesun Ahmed and Zhang, Hao and Mao, Wei and Fukutani, Katsuyuki and Matsuzaki, Hiroyuki and Wen, Lingzhi and Wang, Cong and Zhao, Hongbo and others}, journal = {Matter}, volume = {7}, number = {5}, pages = {1799--1816}, year = {2024}, publisher = {Elsevier}, url = {https://www.cell.com/matter/fulltext/S2590-2385(24)00108-5}, }
ICCIT
Irfd: A feature engineering based ensemble classification for detecting electricity fraud in traditional meters

Md Zesun Ahmed Mia, Md Moinul Islam, Monjurul Haque, and 2 more authors

In 2021 24th International Conference on Computer and Information Technology (ICCIT), 2021

Abs Bib PDF

Nations have suffered significant economic losses as a result of non-technical electric losses resulting from power fraud. It is a criminal act of stealing electricity by applying various mechanisms that incorporate unauthorized tapping to the power line, bypassing the smart meter, etc. Electricity theft is a significant concern for not only developing countries but also developed countries as well. However, for most developing countries, the implications are catastrophic, given that their usage is always less than their demands. Electricity theft must be detected precisely and quickly in order to be mitigated. In our study, we have proposed a method of predictive ensemble machine learning techniques (IRFD) with a novel combination of feature distinction methods to detect electricity theft. In our proposed model, we have combined feature selection technique, Recursive Feature Elimination with Stratified 10-Fold cross-validation (RFECV) and Isolation Forest (IF), to identify and remove outliers along with several machine learning classifiers to forecast the theft of electricity. This study additionally enhances the management of highly imbalanced fraudulent data with Borderline-SMOTE with SVM (SVMSMOTE) and feature scaling with StandardScaler. Following the study, the Random Forest classifier observed a higher degree of accuracy (97.06%) with higher precision, recall, and F1-Score. To evaluate the efficacy of our proposed model, comparative analysis of the classification metrics is also assessed with several machine learning classifiers like Logistic Regression, Gradient Boosting, XGBoost, AdaBoost, KNN, ANN, along with Random Forest before and after fitting our proposed feature engineering techniques.
@inproceedings{mia2021irfd, title = {Irfd: A feature engineering based ensemble classification for detecting electricity fraud in traditional meters}, author = {Mia, Md Zesun Ahmed and Islam, Md Moinul and Haque, Monjurul and Islam, Saiful and Rahman, SMA Mohaiminur}, booktitle = {2021 24th International Conference on Computer and Information Technology (ICCIT)}, pages = {1--6}, year = {2021}, organization = {IEEE}, url = {https://ieeexplore.ieee.org/document/9689842/}, }