Jihoon Tack

About

I am a Ph.D. student at KAIST, advised by Prof. Jinwoo Shin, and a Visiting Ph.D. student at University of Oxford, advised by Prof. Yee Whye Teh. I also work closely with Jonathan Richard Schwarz at DeepMind and Prof. Jaeho Lee at POSTECH. My research interests lies in developing efficient and robust machine learning frameworks. In particular, my recent research focuses on developing efficient pre-training and adaptation algorithms by leveraging useful prior knowledge extracted from multiple tasks, e.g., meta- and continual-learning. I am fortunate to be a recipient of Google Ph.D. Fellowship in machine learning.

Topics of interest (publications with overlap):

Meta-Learning: NeurIPS'23a, NeurIPS'23b, ICML'23, ICLR'23, NeurIPS'22, NeurIPS'21
Neural Field / Implicit Neural Representation: NeurIPS'23a, ICML'23, ICLR'22, NeurIPS'21
Large Language Models: ICMLW'23
Distributional Shift Robustness: SaTML'23, AAAI'22, ICMLW'21, NeurIPS'20a, NeurIPS'20b

Publications

* denotes equal contribution

Learning Large-scale Neural Fields via Context Pruned Meta-Learning

Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder

Semi-supervised Tabular Classification via In-context Learning of Large Language Models

Modality-Agnostic Variational Compression of Implicit Neural Representations

STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables

Rethinking the Entropy of Instance in Adversarial Training

Meta-Learning with Self-Improving Momentum Target

K-centered Patch Sampling for Efficient Video Recognition

Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks

Consistency Regularization for Adversarial Robustness

Meta-Learning Sparse Implicit Neural Representations

Consistency Regularization for Training Confidence-Calibrated Classifiers

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

Adversarial Self-Supervised Contrastive Learning

Education

M.S. & Ph.D. in Artificial Intelligence
Korea Advanced Institute of Science and Technology (KAIST), Mar. 2019 - Feb. 2025 (expected)
Advisor: Prof. Jinwoo Shin

B.S. in Electrical Engineering and Mathematics (minored)
Korea Advanced Institute of Science and Technology (KAIST), Mar. 2014 - Feb. 2019

Work Experience

Visiting Student, University of Oxford, Working with Prof. Yee Whye Teh, Jun. 2023 - Present

Honors & Awards

Google Ph.D. Fellowship 2023, Research Area: Machine Learning
Samsung Humantech Paper Awards 2023, Bronze Prize
Best Paper Award, Korean Artificial Intelligence Association 2021
Qualcomm Innovation Fellowship Korea 2020
Conference Scholar Award: NeurIPS 2023
Reviewer Awards: NeurIPS 2020, CVPR 2021, NeurIPS 2022

Academic Activities

Conference Reviewer: NeurIPS, ICML, ICLR, CVPR, ICCV, AAAI
Journal Reviewer: TMLR, IJCV, IEEE TNNLS, IEEE TIFS, IEEE TIP, ACM TKDD
Workshop Reviewer: AI4CC@CVPR, VAND@CVPR, Neural-Field@ICLR, DistShift@NeurIPS