Jaehyung Kim

🔥 News 

• Apr 2025: Jaehyung will serve as an Area Chair for NeurIPS 2025!

• Jan 2025: Fermi is accepted to NAACL 2025! 

• Jan 2025: SPA is accepted to ICLR 2025 as Oral presentation (207/11672=1.77%)! 

• Sep 2024: Two papers (OCTree and MAC) are accepted to NeurIPS 2024!

• Sep 2024: CoBB🪽 is accepted to EMNLP 2024! See you in Miami 🌴!

• Sep 2024: I'm joining the Department of Artificial Intelligence at Yonsei University as an Assistant Professor! 

📑 Research 

My research goal is to enhance machine learning (ML) and NLP frameworks to be more accurate and reliable in real-world scenarios, by designing proper algorithms. Recently, I’ve been mostly interested in large language models (LLMs), especially in their alignment, adaptation (e.g., personalization), and development. While my recent focus has mainly been on NLP and LLMs, I’m also interested in improving ML frameworks in other domains.

(C: Conference, W: Workshop, P: Preprint, *: Equal contribution)

2025

[C18] Few-shot Personalization of LLMs with Mis-aligned Responses [pdf][code]

• Jaehyung Kim, and Yiming Yang

• Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL) 2025 (Long, Main)

[C17] Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment [pdf][code]

• Dongyoung Kim, Kimin Lee, Jinwoo Shin, and Jaehyung Kim

• International Conference on Learning Representations (ICLR) 2025 (Oral Presentation, 207/11672=1.77%)

[P9] Extracting and Emulsifying Cultural Explanation to Improve Multilingual Capability of LLMs [pdf][code]

• Hamin Koo, and Jaehyung Kim

• Arxiv Preprint 2025 

[W4] ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification [pdf][code]

• Hyunseok Lee*, Seunghyuk Oh*, Jaehyung Kim, Jinwoo Shin, and Jihoon Tack

• International Conference on Learning Representations (ICLR) 2025, Reasoning and Planning for LLMs Workshop 

2024

[C16] Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning [pdf][code]

• Jaehyun Nam*, Kyuyoung Kim*, Seunghyuk Oh, Jihoon Tack, Jaehyung Kim,  and Jinwoo Shin

• Neural Information Processing Systems (NeurIPS) 2024

[C15] Online Adaptation of Language Models with a Memory of Amortized Contexts [pdf][code]

• Jihoon Tack, Jaehyung Kim,  Eric Mitchell, Jinwoo Shin, Yee Whye Teh, and Jonathan Richard Schwarz

• Neural Information Processing Systems (NeurIPS) 2024

[C14] Learning to Correct for QA Reasoning with Black-box LLMs [pdf][code]

• Jaehyung Kim, Dongyoung Kim, and Yiming Yang

• Conference on Empirical Methods in Natural Language Processing (EMNLP) 2024 (Long, Main)

[C13, W3] Tabular Transfer Learning via Prompting LLMs [pdf][code]

• Jaehyun Nam, Woomin Song, Seong Hyeon Park, Jihoon Tack, Sukmin Yun, Jaehyung Kim, Kyu Hwan Oh, and Jinwoo Shin

• Conference on Language Modeling (COLM) 2024

• ICML Workshop on Efficient Systems for Foundation Models (ES-FoMo) 2023

[C12] Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs [pdf][code]

• Woomin Song*, Seunghyuk Oh*, Sangwoo Mo, Jaehyung Kim, Sukmin Yun, Jung-Woo Ha, and Jinwoo Shin

• International Conference on Learning Representations (ICLR) 2024

[C11] SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs [pdf][code][slide][poster]

• Jaehyung Kim, Jaehyun Nam, Sangwoo Mo, Jongjin Park, Sang-Woo Lee, Minjoon Seo, Jung-Woo Ha, and Jinwoo Shin

• International Conference on Learning Representations (ICLR) 2024

[P7, W2] Chain-of-Thoughts for Molecular Understanding [pdf][code]

• Yunhui Jang, Jaehyung Kim,  and Sungsoo Ahn

• Neural Information Processing Systems (NeurIPS) 2024, AIDrugX Workshop

[P6] Can LLMs Generate Diverse Molecules? Towards Alignment with Structural Diversity [pdf][code]

• Hyosoon Jang, Yunhui Jang, Jaehyung Kim,  and Sungsoo Ahn

• Arxiv Preprint 2024

[P3] SelectLLM: Can LLMs Select Important Instructions to Annotate? [pdf][code]

• Ritik Sachin Parkar*, Jaehyung Kim*, Jong Inn Park, and Dongyeop Kang

• Arxiv Preprint 2024

[P2] Under the Surface: Tracking the Artifactuality of LLM-Generated Data [pdf][code][project]

• Debarati Das*, Karin De Langis*, Anna Martin*, Jaehyung Kim*, Minhwa Lee*, Zae Myung Kim*, Shirley Hayati, Risako Owan, Bin Hu, Ritik Parkar, Ryan Koo, Jonginn Park, Aahan Tyagi, Libby Ferland, Sanjali Roy, Vincent Liu, and Dongyeop Kang

• Arxiv Preprint 2024

[W1] Meta-Crafting: Improved Detection of Out-of-distributed Texts via Crafting Metadata Space

• Ryan Koo, Yekyung Kim, Dongyeop Kang, and Jaehyung Kim

• AAAI Conference on Artificial Intelligence (AAAI) Student Abstract and Poster Program 2024

2023

[C10] RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training [pdf][code][slide][poster]

• Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang, and Madian Khabsa

• Conference on Empirical Methods in Natural Language Processing (EMNLP) 2023 (Long, Findings)

[C9] A Universal Framework for Dataset Characterization with Multidimensional Meta-information [pdf][code][slide][poster]

• Jaehyung Kim, Yekyung Kim, Karin Johanna Denton de Langis, Jinwoo Shin, and Dongyeop Kang

• Annual Meeting of the Association for Computational Linguistics (ACL) 2023 (Long, Main)

[C8] Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning [pdf][code][slide][poster]

• Jaehyung Kim,  Jinwoo Shin, and Dongyeop Kang

• International Conference on Machine Learning (ICML) 2023

[C7] Everyone’s Voice Matters: Quantifying Annotation Disagreement Using Demographic Information [pdf][code]

• Ruyuan Wan, Jaehyung Kim, and Dongyeop Kang

• AAAI Conference on Artificial Intelligence (AAAI) 2023 (Oral Presentation)

~ 2022

[C6] Time Is MattEr: Temporal Self-supervision for Video Transformers [pdf][code]

• Sukmin Yun, Jaehyung Kim, Dongyoon Han, Hwanjun Song, Jung-Woo Ha, and Jinwoo Shin

• International Conference on Machine Learning (ICML) 2022

• Winners, Qualcomm Innovation Fellowship Korea 2022

[C5] Patch-level Representation Learning for Self-supervised Vision Transformers [pdf][code]

• Sukmin Yun, Hankook Lee, Jaehyung Kim, and Jinwoo Shin

• Conference on Computer Vision and Pattern Recognition (CVPR) 2022 (Oral Presentation)

[C4] What Makes Better Augmentation Strategies? Augment Difficult but Not too Different [pdf][code][slide][poster]

• Jaehyung Kim, Dongyeop Kang, Sungsoo Ahn, and Jinwoo Shin

• International Conference on Learning Representations (ICLR) 2022

• Silver Prize, Samsung Humantech Paper Awards 2021 

• Winners, Qualcomm Innovation Fellowship Korea 2022

[C3] Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation [pdf]

• Junhyun Nam, Jaehyung Kim, Jaeho Lee, and Jinwoo Shin

• International Conference on Learning Representations (ICLR) 2022

[C2] Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning [pdf][code][slide][poster]

• Jaehyung Kim, Youngbum Hur, Sejun Park, Eunho Yang, Sung Ju Hwang, and Jinwoo Shin

• Neural Information Processing Systems (NeurIPS) 2020

• Winners, Qualcomm Innovation Fellowship Korea 2021 

[C1] M2m: Imbalanced Classification via Major-to-minor Translation [pdf][code][slide]

• Jaehyung Kim*, Jongheon Jeong*, and Jinwoo Shin

• Conference on Computer Vision and Pattern Recognition (CVPR) 2020

[P1] Simplified Stochastic Feedforward Neural Networks [pdf]

• Kimin Lee, Jaehyung Kim, Song Chong, and Jinwoo Shin

• ArXiv Preprint 2017

💻 Work Experiences

Collaborator, Naver AI, Jeongja, South Korea - with Sang-Woo Lee, Minjoon Seo, and Jung-Woo Ha (Nov. 2022 - May. 2023)

Research Intern, Meta AI, Seattle, WA - with Madian Khabsa (May. 2022 - Aug. 2022)

Visiting Student, University of Minnesota, Minneapolis, MN - with Dongyeop Kang (Feb. 2022 - May. 2022)

Visiting Student, Samsung Advanced Institute of Technology, Suwon, South Korea - with Eunho Yang and Sung Ju Hwang (Jan. 2020 - Mar. 2020)

🏆 Awards

• Winner ($5,000),  Qualcomm Innovation Fellowship Korea 2022

• Silver Prize ($7,000), Samsung Humantech Paper Awards 2021 

• Winner ($5,000),  Qualcomm Innovation Fellowship Korea 2021

• 3rd place, ILSVRC (ImageNet Challenge) on Object Detection 2017 

👨‍🎓 Academic Services

Senior Program Committee

• Area Chair, Neural Information Processing Systems (NeurIPS): 2025 

Conference Reviewer

• AAAI Conference on Artificial Intelligence (AAAI): 2021, 2022, 2023

• Association for Computational Linguistics (ACL) Rolling Review: 2022-2025

• Conference on Computer Vision and Pattern Recognition (CVPR): 2023

• Conference on Empirical Methods in Natural Language Processing (EMNLP): 2022, 2023

• International Conference on Learning Representations (ICLR): 2022-2025

• International Conference on Machine Learning (ICML): 2021-2025

• Neural Information Processing Systems (NeurIPS): 2021-2024 

Journal Reviewer

• Transactions on Machine Learning Research (TMLR)

• Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

• IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

🎤 Invited Talks

Beyond the Era of Transformer-based AI Foundation Models

• Samsung Future Technology Research (Oct. 2024)

Designing New Effective Inference Algorithms for Large Language Models

• Amazon Artificial General Intelligence (AGI) (Mar. 2024)

• Ulsan National Institute of Science and Technology (UNIST) (May. 2024) 

Deep Learning with Imbalanced Datasets

• Samsung Electronics Data & Information Technology Center (Oct. 2021)

Multi-aspect Analysis on Data Informativeness

• Summer 2021 Presentation Minnesota NLP Group (Aug. 2021)

Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

• NeurIPS 2020 Social ML in Korea (Dec. 2020)