KiYoon Yoo

Researcher, Krafton

Joined

September 2020

Names

KiYoon Yoo (Preferred)

Emails

****@snu.ac.kr (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Researcher

Krafton (krafton.com)

2024 – Present

PhD student

Seoul National University (snu.ac.kr)

2019 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Nojun Kwak

2019 – 2024

Expertise

Multimodal

LLM

2024 – 2025

Watermarking

2022 – 2023

natural language

2022 – 2023

Safety

2021 – 2023

Adversarial attack and defense

2021 – 2022

Publications

Self-Distilled Self-supervised Representation Learning
Jiho Jang, Seonhoon Kim, KiYoon Yoo, Jangho Kim, Chaerin Kong, Nojun Kwak
- Proceedings of the IEEE/CVF winter conference on applications of computer vision
- Readers: Everyone
Hardware-Friendly Post-Training Quantization: Input- and Output-Channelwise Scale and Offset
Geunjae Choi, Kamin Lee, KiYoon Yoo, Nojun Kwak
- Submitted to ICLR 2024
- Readers: Everyone
Advancing Beyond Identification: Multi-bit Watermark for Large Language Models
KiYoon Yoo, Wonhyuk Ahn, Nojun Kwak
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Self-Distilled Self-supervised Representation Learning
Jiho Jang, Seonhoon Kim, KiYoon Yoo, Chaerin Kong, Jangho Kim, Nojun Kwak
- Published: 01 Jan 2023, Last Modified: 16 May 2023
- WACV 2023
- Readers: Everyone
Robust Natural Language Watermarking through Invariant Features
KiYoon Yoo, Wonhyuk Ahn, Jiho Jang, Nojun Kwak
- Published: 01 Jan 2023, Last Modified: 16 May 2023
- CoRR 2023
- Readers: Everyone
Robust Multi-bit Natural Language Watermarking through Invariant Features
KiYoon Yoo, Wonhyuk Ahn, Jiho Jang, Nojun Kwak
- Published: 01 Jan 2023, Last Modified: 05 Nov 2023
- ACL (1) 2023
- Readers: Everyone
Advancing Beyond Identification: Multi-bit Watermark for Language Models
KiYoon Yoo, Wonhyuk Ahn, Nojun Kwak
- Published: 01 Jan 2023, Last Modified: 05 Nov 2023
- CoRR 2023
- Readers: Everyone
Finding Efficient Pruned Network via Refined Gradients for Pruned Weights
Jangho Kim, Jayeon Yoo, Yeji Song, KiYoon Yoo, Nojun Kwak
- Published: 01 Jan 2023, Last Modified: 05 Nov 2023
- ACM Multimedia 2023
- Readers: Everyone
Backdoor Attacks in Federated Learning by Poisoned Word Embeddings
KiYoon Yoo, Nojun Kwak
- Published: 27 Mar 2022, Last Modified: 05 May 2023
- FL4NLP@ACL2022
- Readers: Everyone
Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation
KiYoon Yoo, Jangho Kim, Jiho Jang, Nojun Kwak
- 2022 (modified: 10 Nov 2022)
- CoRR 2022
- Readers: Everyone

View all 22 publications