profile image

Eunseop Yoon

Ph.D Candidate @ KAIST EE

About Me

I graduated from the Hanyang University, Korea with a B.S. in Electrical Engineering (2021) and from Korea Advanced Institute of Science& Technology (KAIST) with a M.S. (2023). I am currently a Ph.D candidate in KAIST under the guidance of my supervisor professor Chang D. Yoo.

In my research, my focus in on enhancing reliability of AI and Deep Learning tools when working with images, videos, and languages. I really enjoy discovering more about what these tools can do, and I'm always looking for ways to make them work better and reliable in real-world situations. My ultimate goal is to contribute to the development of socially acceptable artificial intelligence through ongoing, in-depth research efforts.

Publication

(* denotes equal contribution)

BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation
Hee Suk Yoon*, Eunseop Yoon*, Joshua Tian Jin Tee*, Kang Zhang, Yu-Jung Heo, Du-Seong Chang, Chang D. Yoo
ECCV 2024

LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition
Eunseop Yoon*, Hee Suk Yoon*, John Harvill, Mark Hasegawa-Johnson, Chang D. Yoo
INTERSPEECH 2024

TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback
Eunseop Yoon*, Hee Suk Yoon*, SooHwan Eom*, Gunsoo Han, Daniel Wontae Nam, Daejin Jo, Kyoung-Woon On, Mark Hasegawa-Johnson, Sungwoong Kim, Chang D. Yoo
ACL 2024 (findings)

C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
Hee Suk Yoon*, Eunseop Yoon*, Joshua Tian Jin Tee, Mark Hasegawa-Johnson, Chang D Yoo
ICLR 2024
[openreview]

ADAMER-CTC: Connectionist Temporal Classification with Adaptive Maximum Entropy Regularization for Automatic Speech Recognition
SooHwan Eom, Eunseop Yoon, Hee Suk Yoon, Chanwoo Kim, Mark Hasegawa-Johnson, Chang D. Yoo
ICASSP 2024

SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation
Hyun Ryu, Sunjae Yoon, Hee Suk Yoon, Eunseop Yoon, Chang D. Yoo
AAAI 2024

One-Shot and Few-Shot Exemplification Modeling
John Harvill, Hee Suk Yoon, Eunseop Yoon, Mark Hasegawa-Johnson and Chang D. Yoo
EMNLP 2023 Workshop on Generation, Evaluation & Metrics (GEM 2023)

HEAR: Hearing Enhanced Audio Response for Video-grounded Dialogue
Sunjae Yoon, Dahyun Kim, Eunseop Yoon, Hee Suk Yoon, Junyeong Kim, and Chang D. Yoo
EMNLP 2023 (findings)
[openreview]

Efficient Latent Variable Modeling for Knowledge-Grounded Dialogue Generation
Gunsoo Han, Daejin Jo, Daniel Wontae Nam, Eunseop Yoon, Taehwan Kwon, Seungeun Rho, Kyoung-Woon On, Chang D. Yoo, Sungwoong Kim
EMNLP 2023 (findings)
[openreview]

Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction
Eunseop Yoon*, Hee Suk Yoon*, Dhananjaya Gowda, SooHwan Eom, Daehyeok Kim, John Harvill, Heting Gao, Mark Hasegawa-Johnson, Chanwoo Kim, Chang D. Yoo
INTERSPEECH 2023
[arxiv]

One-Shot Exemplification Modeling via Latent Sense Representations
John Harvill, Hee Suk Yoon, Eunseop Yoon, Mark Hasegawa-Johnson and Chang D. Yoo
ACL 2023 Workshop on Representation Learning for NLP (RepL4NLP 2023)

INTapt: Information-Theoretic Adversarial Prompt Tuning for Enhanced Non-Native Speech Recognition
Eunseop Yoon*, Hee Suk Yoon*, John Harvill, Mark Hasegawa-Johnson, Chang D. Yoo
ACL 2023 (findings)
[arxiv]

Counterfactual Two-stage Debiasing for Video Corpus Moment Retrieval
Sunjae Yoon, Ji Woo Hong, SooHwan Eom, Hee Suk Yoon, Eunseop Yoon, Daehyeok Kim, Junyeong Kim, Chanwoo Kim, Chang D. Yoo
ICASSP 2023

ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure
Hee Suk Yoon*, Joshua Tian Jin Tee*, Eunseop Yoon, Sunjae Yoon, Gwangsu Kim, Yingzhen Li, Chang D. Yoo
ICLR 2023
[openreview] [arxiv]

SMSMix: Sense Maintained Sentence Mixup for Word Sense Disambiguation
Hee Suk Yoon*, Eunseop Yoon*, John Harvill, Sunjae Yoon, Mark Hasegawa-Johnson, Chang D Yoo
EMNLP 2022 (findings)
[arxiv]

Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue
Sunjae Yoon, Eunseop Yoon, Hee Suk Yoon, Junyeong Kim, Chang D Yoo
EMNLP 2022
[arxiv]

Selective Query-Guided Debiasing for Video Corpus Moment Retrieval
Sunjae Yoon, Ji Woo Hong, Eunseop Yoon, Dahyun Kim, Junyeong Kim, Hee Suk Yoon, Chang D Yoo
ECCV 2022
[arxiv]

Academic Activities

Reviewer Experience

  • ACL Rolling Review : 2023 Dec, 2024
  • Association for Computational Linguistics (ACL) : 2023
  • International Conference on Acoustics, Speech & Signal Processing (ICASSP) : 2023
  • Empirical Methods on Natural Language Processing (EMNLP) : 2023
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) : 2023, 2024
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)

Teaching Assistance

  • Statistical Learning Theory : 2024 Spring
  • Technical Writing : 2023 Fall
  • Seongnam-KAIST Next Generation ICT Research Center Machine Learning and Big Data Course : 2022, 2023
  • Hwaseong City-KAIST Semiconductor Specialized Curriculum - Large Language Models : 2023
  • Hwaseong City-KAIST AI Specialized Curriculum - Large Language Models : 2024 Spring

Projects

Development of Uncertainty-Aware Agents Learning by Asking Questionn
2022-03-01 ~ 2027-03-01
Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government

Multi-modal Generative AI for Summarization
2023-09-01 ~ 2024-09-01
Samsung Speech Recognition & Natural Language Processing Lab

Visual Dialogue System: Developing Visual and Language Capabilities for AI-Based Dialogue Systems
2022-11-01~
Korea Telecom (KT) AI2XL Laboratory