Hanseok Oh

About

Hello! I am currently working as a AI Research Engineer at SoftlyAI. Before that I earned my M.S. degree from the Language & Knowledge Lab at KAIST, advised by Minjoon Seo. I am interested in building personalized assistants to aid user experiences for solving real-world problem by efficiently encoding, accessing, and leveraging knowledge.

News

May 2024 Starting a new position as a Research Engineer at SoftlyAI!

Feb 2024 Our Ktrl+F paper has been accepted to NAACL 2024! See you in Mexico :).

Feb 2024 Currently seeking opportunities in a research scientist/engineer role.

Feb 2024 New preprint INSTRUCTIR is out!

Nov 2023 New preprint Ktrl+F is out!

Sep 2023 Joining LG AI research as a Research Intern!

May 2023 Our Nonparametric Decoding for Generative Retrieval has been accepted to ACL 2023 Findings!

Feb 2023 Our Structured abstract summarization of scientific articles: Summarization using full-text section information paper has been accepted to JASIST 2022!

October 2022 Our Generative Multi-hop Retrieval paper has been accepted to EMNLP 2022! See you in Abu Dhabi (12.7 - 12.12) :)

Jan 2022 Our team got a 1st place at ICCV 2021 VALUE Challenge Retrieval Track! ViSeRet paper has been accepted to ICCV 2021 Workshop on Closing the Loop between Vision and Language (CLVL)!

Education

Korea Advanced Institute of Science and Technology (KAIST) Sep. 2021 - Feb. 2024

M.S. Student (advisor: Minjoon Seo)

Sungkyunkwan UniversityMar. 2014 - Aug. 2020

B.S. of Data Science & B.A. in Child and Adolescent education

Publications

The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models

Seungone Kim, Juyoung Suk, Ji Yong Cho, Shayne Longpre, ..., Hanseok Oh, … , Sean Welleck, Graham Neubig, Moontae Lee, Kyungjae Lee, and Minjoon Seo arXiv preprint

Preprint

Paper

INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval Models

Hanseok Oh, Hyunji Lee, Seonghyeon Ye, Haebin Shin, Hansol Jang, Changwook Jun, Minjoon Seo

ACL 2024 Workshop on Knowledge-Augmented NLP (KnowledgeNLP) | (WIP)

Paper Code Twitter

Ktrl+F: Knowledge-Augmented In-Document Search

Hanseok Oh*, Haebin Shin*, Miyoung Ko, Hyunji Lee, Minjoon Seo

NAACL 2024

Paper Code Twitter

Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment

Yongrae Jo, Seongyun Lee, Aiden SJ Lee, Hyunji Lee, Hanseok Oh, Minjoon Seo

Preprint

Paper

Structured Abstract Summarization of Scientific Articles: Summarization Using Full-text Section Information

Hanseok Oh, Seojin Nam, Yongjun Zhu

JASIST (2022)

Paper

Nonparametric Decoding for Generative Retrieval

Hyunji Lee, Jaeyoung Kim, Hoyeon Chang, Hanseok Oh, Sohee Yang, Vlad Karpukhin, Yi Lu, Minjoon Seo

ACL 2023 Findings

Paper

Generative Multi-hop Retrieval

Hyunji Lee, Sohee Yang, Hanseok Oh, Minjoon Seo

EMNLP 2022

Paper Code Twitter

ViSeRet: A simple yet effective approach to moment retrieval via fine-grained video segmentation

Aiden Seungjoon Lee, Hanseok Oh, Minjoon Seo

ICCV 2021 Workshop on Closing the Loop between Vision and Language (CLVL)

Paper

***( * indicates equal contribution )***

Vitæ

SoftlyAI May. 2024 - Present

Research Engineer
Building AI agents for professional needs
LG AI Research Sep. 2023 - Feb. 2024

Research Intern
Working on exploring ways to efficiently utilize non-parametric knowledge
KAIST Language & Knowledge Lab Sep. 2021 - Feb. 2024

M.S. Student (Advisor: Minjoon Seo)
Working on advanced information retrieval system
Kakao Enterprise Jul. 2020 - Oct. 2020

Machine Learninig Engineer Intern
Worked on large-scale knoweldge graph embedding
NAVER Mar. 2020 - Jun. 2020

Software Engineer Intern
Worked on entity linking engine for the search system
Sungkyunkwan University Mar. 2014 - Aug. 2020

B.S. of Data Science & B.A. in Child and Adolescent education