Si Yong Lee.

Ph.D. student · Stony Brook University

Si Yong Lee.

Efficient intelligence,
inspired by the brain.

I study how sparse events can power intelligent systems — from spiking neural networks to efficient sequence models and neuromorphic hardware.

Explore my research
Google Scholar LinkedIn Email
Si Yong Lee standing in a sunlit courtyard.
Si Yong LeeStony Brook University
Neuromorphic computing   /   Spiking networks   /   Sequence modelingScroll to explore

01 / About

Doing more.
Computing less.

Conceptual illustration: a continuous signal becomes sparse spikes that selectively update a recurrent state.

I am a Ph.D. student in Computer Science at Stony Brook University, advised by Prof. Yoon Seok Yang in the Brain-Inspired Computing Lab.

My research connects neuromorphic computing and machine learning. I build spiking neural networks and state space models that use sparse, event-driven computation, with a particular interest in biomedical signals and practical on-device deployment.

Previously, I earned my M.S. in Computer Science and Engineering at Chungnam National University, advised by Prof. Hyungshin Kim. I am also a co-founder and Principal Software Engineer at MindSyn.

01 Event-driven learning02 Efficient sequence models03 On-device intelligence

02 / Research

Ideas into systems.

Selected work in efficient learning,
biomedical AI, and neuromorphic computing.

Under reviewSequence modeling

Pay at the Event: Event-Conditioned Recurrent State Tracking and Associative Recall

Si Yong Lee, R. Lee, Yoon Seok Yang

Allocating transition computation at selected events, with fixed-size associative storage for recall.

Under reviewOn-device deployment

Firefly: Multiplier-Free Spiking State-Space Models for Bit-Exact Parallel On-Device Deployment

Si Yong Lee, H. Park, R. Lee, Yoon Seok Yang

An integer spike pipeline connecting parallel training with bit-exact sequential execution on neuromorphic hardware.

ICONIP 2026Accepted

TFST: A Hardware-Aware Spiking Transformer for On-Device Biomedical Time-Series Inference

R. Lee, H. Park, Si Yong Lee, Y. Kim, Yoon Seok Yang

IEEE Access · 2026

Advanced Training Algorithms in Sigma-Delta Spiking YOLO for Energy-Efficient Object Detection on Neuromorphic Hardware

D. Kim, G. Kim, M. Kim, Si Yong Lee, Yoon Seok Yang

MCSoC 2025

MindCore: Spike-Driven Programmable Accelerator for On-Device Neuromorphic Computing

H. Park, Si Yong Lee, R. Lee, Y. Kim, Yoon Seok Yang

Under revisionBiomedical AI

Adaptive Population-Encoded Spiking Neural Networks on a Neuromorphic Processor for Chest CT Classification

Si Yong Lee, B. Kang, Yoon Seok Yang

Under revisionBiomedical AI

A Low-Power, Real-Time, and Noise-Resilient Spiking Neural Network for Bio-Signal Classification on a Neuromorphic Processor

Si Yong Lee*, Y. Kim*, Yoon Seok Yang (* Equal contribution)

03 / Background

Along the way.

Full curriculum vitae

Education

Aug 2024 — Present

Stony Brook University

Ph.D. in Computer Science

Advisor: Yoon Seok Yang

Aug 2024

Chungnam National University

M.S. in Computer Science and Engineering

Advisor: Hyungshin Kim

Feb 2022

Jeonbuk National University

B.S. in Environmental Biotechnology

Research & industry

May 2026 — Present

MindSyn

Co-founder · Principal Software Engineer

Aug 2024 — Present

Brain-Inspired Computing Lab

Full-time Research Assistant

Jun 2022 — Mar 2024

iJoon

Software & AI Engineer

Teaching

Teaching Assistant, Stony Brook University
CSE320 & CSE416 · Aug–Dec 2025

04 / Connect

Let’s make
every event count.

Interested in efficient learning or neuromorphic computing?
I’d be happy to talk research.

siyong.lee@stonybrook.edu

Research figure

Download SVG ↓