Seongbo Jang

Curriculum Vitae  |  Biography

profile.jpg

Postdoc at POSTECH

I am currently a postdoctoral researcher at Data Intelligence (DI) Lab at Pohang University of Science and Technology (POSTECH). Here, I received my Ph.D. in Computer Science and Engineering under the supervision of Prof. Hwanjo Yu.

During my Ph.D., I was fortunate to join Scatter Lab Inc. and contribute to the development of Luda Lee, a social companion chatbot, and Zeta, an AI storytelling platform, both of which serve over several million users.

My research aims to develop human-friendly AI agents endowed with social intelligence. Toward this goal, I have worked on multimodal agents, evaluation methods for social intelligence, and the construction of benchmarks and large-scale synthetic datasets to model desirable human-like behaviors.

Research Interests

Human-like behaviors in social companion chatbots
Social intelligence of dialogue agents
Multimodal dialogue systems

News

Sep, 2025 Started my postdoctoral research position at POSTECH.
Aug, 2025 Received my Ph.D. in Computer Science and Engineering at POSTECH.
Apr, 2025 Successfully defended my Ph.D. dissertation.
Feb, 2024 Our paper (KoDialogBench) was accepted to LREC-COLING 2024.
Jan, 2024 Joined DLI Lab at Yonsei University as a visiting scholar.

Publications

  1. From What to Respond to When to Respond: Timely Response Generation for Open-domain Dialogue Agents
    Seongbo Jang, Minjin Jeon, Jaehoon Lee, Seonghyeon Lee, Dongha Lee, and Hwanjo Yu
    arXiv preprint, 2025
    Paper Code
  2. On the Effectiveness of Integration Methods for Multimodal Dialogue Response Retrieval
    Seongbo Jang, Seonghyeon Lee, Dongha Lee, and Hwanjo Yu
    arXiv preprint, 2025
    Paper
  3. Exploring Language Model’s Code Generation Ability with Auxiliary Functions
    Seonghyeon Lee, Sanghwan Jang, Seongbo Jang, Dongha Lee, and Hwanjo Yu
    NAACL Findings, 2024
    Paper Code
  4. KoDialogBench: Evaluating Conversational Understanding of Language Models with Korean Dialogue Benchmark
    Seongbo Jang*, Seonghyeon Lee*, and Hwanjo Yu
    LREC-COLING, 2024
    Paper Code
  5. Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning
    Seonghyeon Lee, Dongha Lee, Seongbo Jang, and Hwanjo Yu
    ACL, 2022
    Paper Code
  6. KLUE: Korean Language Understanding Evaluation
    Sungjoon Park*, Jihyung Moon*, Sungdong Kim*, Won Ik Cho*, Ji Yoon Han, Jangwon Park, and 25 more authors
    NeurIPS Datasets and Benchmarks, 2021
    Paper Code Website
  7. An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks
    Kyubyong Park*, Joohong Lee*, Seongbo Jang*, and Dawoon Jung*
    AACL-IJCNLP, 2020
    Paper Code
  8. Input initialization for inversion of neural networks using k-nearest neighbor approach
    Seongbo Jang, Ye-Eun Jang, Young-Jin Kim, and Hwanjo Yu
    Information Sciences, 2020
    Paper

Experience

  • Sep 2025 - Present

    Pohang, South Korea

    Postdoctoral Researcher
    Data Intelligence (DI) Lab @ POSTECH
  • Jan 2024 - Aug 2025

    Seoul, South Korea

    Visiting Scholar
    Data & Language Intelligence (DLI) Lab @ Yonsei University
    Conducted research on timing-aware responses of open-domain dialogue systems
  • Feb 2022 - Dec 2023

    Seoul, South Korea

    Machine Learning Researcher
    Scatter Lab, Inc.
    Contributed to the development of multimodal generative models for Luda Lee and Zeta
  • Aug 2019 - Feb 2022

    Seoul, South Korea

    Visiting Researcher
    Scatter Lab, Inc.
    Contributed to the development of response ranking models for Luda Lee, a social companion chatbot
  • Aug 2016 - Feb 2017

    Pohang, South Korea

    Research Intern
    DI Lab @ POSTECH
    Developed a sentiment analysis web demo for online forums

Education