Hover portrait
Taekyun Lee
Portrait Hover portrait
Ph.D. Student in Electrical and Computer Engineering
The University of Texas at Austin (WNCG)

Hi, my name is Taekyun Lee. I am a Ph.D. student in Electrical and Computer Engineering at The University of Texas at Austin (WNCG), advised by Prof. Jeffrey Andrews and Prof. Hyeji Kim. I received my B.S. in Electrical and Computer Engineering from Seoul National University in February 2022.

My main research area is Wireless Communication and Diffusion Models (continuous or discrete).

Google Scholar GitHub LinkedIn
Education
  • University of Texas at Austin
    University of Texas at Austin
    Wireless Networking and Communications Group (WNCG)
    M.S. & Ph.D. in Electrical and Computer Engineering
    Advisors: Jeffrey G. Andrews, Hyeji Kim
    2022 - Present
  • Seoul National University
    Seoul National University
    Department of Electrical and Computer Engineering
    B.S. in Electrical and Computer Engineering
    Summa Cum Laude
    2016 - 2022
  • Seoul Science High School
    Seoul Science High School
    2013 - 2015
Experience
  • NVIDIA
    NVIDIA
    Santa Clara, CA
    Graduate Research Intern
    May 2026 - Aug 2026
  • NVIDIA
    NVIDIA
    Santa Clara, CA
    Graduate Research Intern
    May 2025 - Aug 2025
  • Keysight
    Keysight
    Santa Rosa, CA
    Graduate Research Intern
    May 2023 - Jul 2023
  • Dudaji
    Dudaji
    Seoul, South Korea
    Undergraduate Research Intern
    Jun 2021 - Jun 2022
News
Our paper "Fine-Tuning Masked Diffusion for Provable Self-Correction" was accepted to ICLR Workshop MM Intelligence (co-first author)!
Mar 2026
Our paper "Efficient Weighted Sampling via Score-based Generative Models" was accepted to IEEE/CVF CVPR 2026 (co-first author)!
Feb 2026
Our paper "Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks" received Spotlight at NeurIPS 2025!
Aug 2025
Received WNCG Student Leadership Award!
May 2025
Started my research internship at NVIDIA!
Apr 2025
My first journal paper "Generating High Dimensional User-Specific Wireless Channels using Diffusion Models" was accepted to IEEE Transactions on Wireless Communications!
Aug 2024
Started my research internship at Keysight Technologies!
Apr 2023
Started my Ph.D. program at UT Austin with Kwanjeong Scholarship!
Jul 2022
Selected Publications (view all )
Efficient Weighted Sampling via Score-based Generative Models
Efficient Weighted Sampling via Score-based Generative Models

Heasung Kim*, Taekyun Lee*, Hyeji Kim, Gustavo de Veciana (* equal contribution)

IEEE/CVF CVPR 2026

[Paper]

Efficient Weighted Sampling via Score-based Generative Models

Heasung Kim*, Taekyun Lee*, Hyeji Kim, Gustavo de Veciana (* equal contribution)

IEEE/CVF CVPR 2026

[Paper]

Fine-Tuning Masked Diffusion for Provable Self-Correction
Fine-Tuning Masked Diffusion for Provable Self-Correction

Jaeyeon Kim*, Seunggeun Kim*, Taekyun Lee*, David Z. Pan, Hyeji Kim, Sham Kakade, Sitan Chen (* equal contribution)

ICLR Workshop MM Intelligence 2026

[Paper] [Code]

Fine-Tuning Masked Diffusion for Provable Self-Correction

Jaeyeon Kim*, Seunggeun Kim*, Taekyun Lee*, David Z. Pan, Hyeji Kim, Sham Kakade, Sitan Chen (* equal contribution)

ICLR Workshop MM Intelligence 2026

[Paper] [Code]

Generating High Dimensional User-Specific Wireless Channels using Diffusion Models
Generating High Dimensional User-Specific Wireless Channels using Diffusion Models

Taekyun Lee, Juseong Park, Hyeji Kim, Jeffrey G. Andrews

IEEE Transactions on Wireless Communications

[Paper] [Code]

Generating High Dimensional User-Specific Wireless Channels using Diffusion Models

Taekyun Lee, Juseong Park, Hyeji Kim, Jeffrey G. Andrews

IEEE Transactions on Wireless Communications

[Paper] [Code]

Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks
Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks

Heasung Kim, Taekyun Lee, Hyeji Kim, Gustavo de Veciana

NeurIPS 2025 Spotlight

[Paper]

Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks

Heasung Kim, Taekyun Lee, Hyeji Kim, Gustavo de Veciana

NeurIPS 2025 Spotlight

[Paper]

DiffLoc: Diffusion Model-Based High-Precision Positioning for 6G Networks
DiffLoc: Diffusion Model-Based High-Precision Positioning for 6G Networks

Taekyun Lee, Tommaso Balercia, Heasung Kim, Hyeji Kim, Jeffrey G. Andrews

ArXiv 2025

[Paper]

DiffLoc: Diffusion Model-Based High-Precision Positioning for 6G Networks

Taekyun Lee, Tommaso Balercia, Heasung Kim, Hyeji Kim, Jeffrey G. Andrews

ArXiv 2025

[Paper]

All publications