Taesun Yeom

I'm a second-year M.S.–Ph.D. student at EffL (Efficient Learning Lab), POSTECH (advisor: Prof. Jaeho Lee). For my research, I primarily focus on understanding various phenomena that arise in deep neural networks.

My recent research interests focus on the theoretical analysis of deep learning, particularly on connecting implicit bias, learning dynamics, and generalization.

Before joining EffL, I received my bachelor's degree in Mechanical Engineering from Chung-Ang University and worked closely with Prof. Minhyeok Lee and Prof. Seokwon Lee.

Email | GitHub | Google Scholar | LinkedIn | CV

Publications

• Generalization Analysis of Linear Knowledge Distillation
  Taesun Yeom, Tahyeok Ha, and Jaeho Lee
  Under review, 2026

• Activation Quantization of Vision Encoders Needs Prefixing Registers
  Seunghyeon Kim, Taesun Yeom, Jinho Kim, Wonpyo Park, Kyuyeun Kim, and Jaeho Lee
  Under review, 2025
  arxiv

• Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization
  Taesun Yeom, Taehyeok Ha, and Jaeho Lee
  ICML, 2026
  arxiv

• On the Internal Representations of Graph Metanetworks
  Taesun Yeom and Jaeho Lee
  ICLR Workshop on Weight Space Learning, 2025
  arxiv | openreview

• Fast Training of Sinusoidal Neural Fields via Scaling Initialization
  Taesun Yeom*, Sangyoon Lee*, and Jaeho Lee
  ICLR, 2025
  arxiv | code | openreview

• DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion
  Taesun Yeom, Chanhoe Gu, and Minhyeok Lee
  IEEE Access, 2024
  paper | code

• Superstargan: Generative adversarial networks for image-to-image translation in large-scale domains
  Kanghyeok Ko, Taesun Yeom, and Minhyeok Lee
  Neural Networks, 2023
  paper | code

Education

• M.S.–Ph.D. in Artificial Intelligence
  Pohang University of Science and Technology (POSTECH), South Korea
  2024.09 – Present

• B.S. in Mechanical Engineering
  Chung-Ang University, South Korea
  2018.03 – 2024.08

Teaching Experience

• Teaching assistant for POSTECH EECE454-01 Intro. to Machine Learning Systems (Fall 2025).

• Teaching assistant for POSTECH EECE695D Deep Learning Theory (Fall 2024).

Services

• Reviewer for NeurIPS, ICML, ECCV, IEEE journals.